From 5405d7f7dcf624cef04b21bfc0fef05dff2f3ab6 Mon Sep 17 00:00:00 2001 From: Rick McEwen Date: Tue, 3 Mar 2026 18:44:49 -0700 Subject: [PATCH] Add accuracy test framework, prompts, results, and analysis reports Includes accuracy test scripts for Qwen (local) and Gemini (cloud API), three prompt variants (original, capstone, constrained), test results from all runs, and two analysis reports with an HTML presentation version. --- .python-version | 1 + accuracy_analysis_report.md | 170 + accuracy_analysis_report_round2.html | 760 ++++ accuracy_analysis_report_round2.md | 229 ++ accuracy_test_results.md | 490 +++ accuracy_test_results_all.txt | 5609 ++++++++++++++++++++++++++ jersey_prompt_capstone.txt | 15 + jersey_prompt_constrained.txt | 56 + pyproject.toml | 11 + run_all_accuracy_tests.sh | 44 + test_accuracy.py | 402 ++ test_accuracy_gemini.py | 576 +++ uv.lock | 198 + 13 files changed, 8561 insertions(+) create mode 100644 .python-version create mode 100644 accuracy_analysis_report.md create mode 100644 accuracy_analysis_report_round2.html create mode 100644 accuracy_analysis_report_round2.md create mode 100644 accuracy_test_results.md create mode 100644 accuracy_test_results_all.txt create mode 100644 jersey_prompt_capstone.txt create mode 100644 jersey_prompt_constrained.txt create mode 100644 pyproject.toml create mode 100755 run_all_accuracy_tests.sh create mode 100644 test_accuracy.py create mode 100644 test_accuracy_gemini.py create mode 100644 uv.lock diff --git a/.python-version b/.python-version new file mode 100644 index 0000000..e4fba21 --- /dev/null +++ b/.python-version @@ -0,0 +1 @@ +3.12 diff --git a/accuracy_analysis_report.md b/accuracy_analysis_report.md new file mode 100644 index 0000000..829e9aa --- /dev/null +++ b/accuracy_analysis_report.md @@ -0,0 +1,170 @@ +# Jersey Color Detection Accuracy Analysis + +## Test Configuration + +- **Models tested:** Gemini 3 Flash Preview (cloud API), Qwen3-VL-8B (local, via llama.cpp) +- **Prompts tested:** `jersey_prompt.txt` (original), `jersey_prompt_capstone.txt` (capstone) +- **Test images:** 161 annotated basketball jersey images +- **Ground truth colors:** 202 (excluding white) +- **Images resized** to max 768px wide before submission + +--- + +## Summary Comparison + +| Metric | Gemini + Original | Gemini + Capstone | Qwen + Original | Qwen + Capstone | +|----------------------------|:-----------------:|:-----------------:|:----------------:|:---------------:| +| **Recall (exact)** | 64.4% | 60.9% | 64.4% | 65.8% | +| **Recall (exact+similar)** | **81.2%** | 78.2% | 77.2% | 77.7% | +| **Recall (missed)** | 18.8% | 21.8% | 22.8% | 22.3% | +| **Precision (exact)** | 74.7% | 70.7% | 70.7% | 73.9% | +| **Precision (exact+sim.)** | **93.7%** | 90.2% | 84.8% | 87.2% | +| **Extra/wrong** | **6.3%** | 9.8% | 15.2% | 12.8% | +| PASS images | **124** | 118 | 117 | 119 | +| PARTIAL images | 19 | 21 | 18 | 19 | +| FAIL images | **18** | 22 | 26 | 23 | +| Avg time per image | 13.3s | 11.7s | 9.5s | 8.9s | + +### Key Takeaways + +1. **Gemini + original prompt is the best combination** across all major metrics: highest recall (81.2%), highest precision (93.7%), fewest failures (18), and fewest extra/wrong colors (6.3%). + +2. **Exact recall is remarkably stable** across all four runs (60.9%–65.8%), suggesting ~35% of ground truth colors are inherently difficult for current VLMs regardless of model or prompt. + +3. **Gemini produces far fewer hallucinated colors** than Qwen. Gemini's extra/wrong rate is 6.3%–9.8% vs. Qwen's 12.8%–15.2%. When Gemini detects a color, it is almost always correct. + +4. **The capstone prompt did not improve results** for either model. For Gemini it degraded both recall and precision. For Qwen the difference was negligible. + +5. **Qwen is ~30% faster** (8.9–9.5s vs 11.7–13.3s per image) but at the cost of lower accuracy and more false positives. + +--- + +## Color-Level Analysis + +### Most Problematic Ground Truth Colors + +Colors most frequently missed across all four test runs: + +| Color | Gemini+Orig | Gemini+Cap | Qwen+Orig | Qwen+Cap | Total Misses | Common Confusion | +|-----------------|:-----------:|:----------:|:---------:|:--------:|:------------:|---------------------| +| **gray** | 7 | 6 | 7 | 9 | 29 | Often returned as "grey" (similar match) or missed entirely | +| **maroon** | 5 | 9 | 8 | 7 | 29 | Frequently confused with "red" | +| **black** | 7 | 7 | 6 | 6 | 26 | Often not detected at all | +| **light blue** | 2 | 2 | 8 | 5 | 17 | Returned as "blue" (Qwen especially) | +| **green** | 3 | 4 | 3 | 4 | 14 | Sometimes returned as "black" | +| **dark brown** | 0 | 1 | 4 | 4 | 9 | Returned as "black" or "brown" | +| **brown** | 1 | 1 | 3 | 3 | 8 | Returned as "black" or "orange" | +| **teal** | 2 | 2 | 2 | 2 | 8 | Confused with "green" or "blue" | +| **blue** | 3 | 3 | 3 | 2 | 11 | Sometimes not detected at all | +| **gold/yellow** | 2 | 2 | 1 | 1 | 6 | Occasionally missed entirely | + +### Most Common Extra/Wrong Colors Reported + +| Extra Color | Gemini+Orig | Gemini+Cap | Qwen+Orig | Qwen+Cap | Notes | +|--------------|:-----------:|:----------:|:---------:|:--------:|-------| +| **red** | 3 | 7 | 7 | 6 | Typically a misread of maroon | +| **black** | 2 | 4 | 7 | 7 | Misread of dark brown/green/gray | +| **blue** | 3 | 2 | 10 | 6 | Misread of light blue or teal | +| **green** | 1 | 1 | 1 | 1 | Misread of teal | +| **orange** | 1 | 1 | 1 | 1 | Misread of brown | + +### Similar-Match Confusion Patterns + +These are cases where the VLM returned a color in the same family but not the exact ground truth term: + +| Expected | Returned As | Gemini+Orig | Gemini+Cap | Qwen+Orig | Qwen+Cap | +|------------------|----------------|:-----------:|:----------:|:---------:|:--------:| +| gray | grey | 9 | 10 | — | — | +| navy blue | blue | 7 | 6 | 8 | 8 | +| dark blue | blue | 5 | 6 | 10 | 9 | +| dark brown | brown | 5 | 5 | 2 | 2 | +| gold | yellow | 3 | 2 | 5 | 3 | +| dark blue | navy blue/navy | 4 | 4 | — | 1 | + +**Observations:** +- **gray/grey** is purely a spelling variant — Gemini consistently uses British spelling. Qwen uses "gray" so this never triggers for Qwen. +- **navy blue → blue** and **dark blue → blue** are the most common simplifications. Both models tend to drop shade qualifiers. +- **dark brown → brown** follows the same pattern of dropping the shade qualifier. +- **gold → yellow** is a genuine color perception difference where models see yellow-dominant gold jerseys. + +--- + +## Persistently Failed Images + +These 11 images failed across **all four** test runs, representing the hardest cases: + +| Image | GT Colors | Typical VLM Response | Failure Pattern | +|-------|-----------|---------------------|-----------------| +| 016 - maroon.jpg | maroon | (none) or red | Maroon not recognized | +| 029 - maroon_white.jpg | maroon | red | Maroon → red confusion | +| 034 - light blue.jpg | light blue | blue | Shade qualifier dropped | +| 046 - green.jpg | green | black | Dark green misread as black | +| 053 - black_white.jpg | black | (not detected) | Black jerseys missed | +| 057 - gold or yellow.jpg | gold\|yellow | (not detected) | Gold/yellow missed | +| 132 - brown_white.jpg | brown | orange | Brown → orange confusion | +| 134 - teal_white.jpg | teal | blue or green | Teal not in model vocabulary | +| 138 - maroon.jpg | maroon | red | Maroon → red confusion | +| 150 - green_gray.jpg | green, gray | black | Both colors misread | +| 160 - blue_white.jpg | blue | (not detected) | Blue not detected | + +### Root Cause Categories + +1. **Maroon blindness (3 images):** Both models consistently classify maroon as red. This is the single largest systematic error. + +2. **Dark color confusion (3 images):** Dark green, brown, and black are frequently confused with each other, especially in low-contrast or shadowed images. + +3. **Shade qualifier loss (2 images):** "Light blue" and "teal" are simplified to "blue" or "green" — models use a coarser color vocabulary than the ground truth. + +4. **Non-detection (3 images):** Some jerseys are simply not detected at all, likely due to occlusion, unusual angles, or low image quality. + +--- + +## Model-Specific Observations + +### Gemini 3 Flash +- **Strengths:** Highest precision (93.7%), very few hallucinated colors, good at similar-family matching. Never produced gibberish color names. +- **Weaknesses:** Consistently uses British "grey" instead of "gray". Slower than local model. +- **Prompt sensitivity:** The capstone prompt slightly hurt performance (81.2% → 78.2% recall), suggesting the original simpler prompt works better. + +### Qwen3-VL-8B +- **Strengths:** Faster inference (8.9s avg). Slightly higher exact match rate with capstone prompt (65.8%). +- **Weaknesses:** Much higher false positive rate (12.8–15.2% extra/wrong). Struggles significantly with "light blue" (8 misses with original prompt). Produced one gibberish color ("redolas"). Over-reports "blue" and "black". +- **Prompt sensitivity:** Minimal difference between prompts. Capstone prompt slightly reduced errors. + +--- + +## Recommendations + +1. **Normalize "grey" → "gray"** in post-processing to eliminate the most common similar-match gap for Gemini. + +2. **Add "maroon" to the prompt** as an explicit color option or example, since both models struggle to distinguish it from red without guidance. + +3. **Consider a constrained color vocabulary** in the prompt (e.g., "Choose from: red, blue, green, yellow, orange, purple, black, gray, brown, maroon, teal, light blue, navy blue, gold, pink") to reduce vocabulary mismatch and shade-qualifier drift. + +4. **Post-processing color mapping** could recover many similar-match cases automatically: navy→navy blue, grey→gray, dark blue→navy blue, etc. + +5. **The original `jersey_prompt.txt` is the better prompt** — the capstone prompt's additional constraints did not improve accuracy for either model. + +--- + +## Appendix: Color Similarity Families + +The following color families were used for "similar match" scoring. Two colors count as a similar match if they appear in the same family: + +| Family | Member Colors | +|------------|-------------------------------------------------------| +| blue | blue, dark blue, navy blue, navy, royal blue | +| light_blue | light blue, sky blue, baby blue, carolina blue, powder blue | +| red | red, scarlet, crimson | +| dark_red | maroon, burgundy, dark red, wine | +| green | green, dark green, forest green, kelly green | +| yellow | yellow, gold, golden | +| orange | orange, burnt orange | +| brown | brown, dark brown | +| purple | purple, violet | +| gray | gray, grey, silver, charcoal | +| black | black | +| teal | teal, turquoise, cyan, aqua | +| pink | pink, magenta, hot pink, rose | + +**Note:** Colors in *different* families are never counted as similar, even if perceptually close (e.g., maroon and red are in separate families; brown and orange are in separate families). This is intentional — the similar-match metric captures vocabulary variation within the same color concept, not genuine color misidentification. diff --git a/accuracy_analysis_report_round2.html b/accuracy_analysis_report_round2.html new file mode 100644 index 0000000..03df706 --- /dev/null +++ b/accuracy_analysis_report_round2.html @@ -0,0 +1,760 @@ + + + + + +Jersey Color Detection Accuracy — Round 2 Analysis + + + + +

Jersey Color Detection Accuracy — Round 2 Analysis

+
+ Date: March 3, 2026
+ Models: Gemini 3 Flash Preview, Qwen3-VL-8B (local via llama.cpp)
+ Prompts: jersey_prompt.txt (original), jersey_prompt_capstone.txt (capstone), jersey_prompt_constrained.txt (constrained)
+ Test set: 161 annotated images, 202 ground truth colors (excluding white) +
+ +
+ +

Summary Comparison

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
MetricQwen OriginalQwen CapstoneQwen ConstrainedGemini OriginalGemini CapstoneGemini Constrained
Recall (exact)65.3%66.3%71.8%62.4%60.9%67.8%
Recall (exact+similar)78.2%78.2%82.7%79.7%78.2%81.7%
Missed21.8%21.8%17.3%20.3%21.8%18.3%
Precision (exact)71.7%74.0%78.4%72.0%69.5%78.7%
Precision (exact+sim.)85.9%87.3%90.3%91.4%88.7%94.3%
Extra/wrong14.1%12.7%9.7%8.6%11.3%5.7%
PASS118120127120117124
PARTIAL191915202219
FAIL242219212218
Total time1557s1437s1596s253s260s344s
+ +
+ +

Key Findings

+ +

1. The constrained prompt is the best prompt for both models

+ +

The constrained vocabulary prompt delivered the strongest results across the board:

+ +
+ Qwen + Constrained + Achieved the highest recall of any combination at 82.7% (167/202 found), up from 78.2% with both other prompts. It also posted the most PASS images (127, up from 118/120) and the fewest FAIL images (19, down from 24/22). +
+ +
+ Gemini + Constrained + Achieved the highest precision of any combination at 94.3% (164/174 correct), with only 5.7% extra/wrong colors — the lowest error rate across all six runs. It tied for fewest failures at 18. +
+ +

2. Exact match rates jumped significantly

+ +

The constrained prompt's biggest impact was converting similar matches into exact matches by forcing models to use the ground truth vocabulary:

+ + + + + + + + + + + + + + + + + + + + + + + + +
ModelExact Match (Original)Exact Match (Constrained)Improvement
Qwen65.3% (132)71.8% (145)+6.5 pp
Gemini62.4% (126)67.8% (137)+5.4 pp
+ +

This came partly from eliminating vocabulary mismatch (e.g., grey→gray, navy→navy blue) and partly from teaching models to use specific color terms like "maroon" and "light blue."

+ +

3. Targeted color improvements

+ +

The constrained prompt's explicit color guidance fixed the worst systematic errors:

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Problem ColorQwen Misses (Orig→Constrained)Gemini Misses (Orig→Constrained)
maroon8 → 36 → 3
light blue7 → 13 → 1
dark brown4 → 21 → 1
teal2 → 22 → 2
gray7 → 86 → 6
black6 → 67 → 7
+ + + +

4. New overcorrection pattern with constrained prompt

+ +
+ Overcorrection Warning + The constrained prompt introduced a new failure mode — models now occasionally over-apply newly-learned color terms. +
+ + + +

This overcorrection is a smaller problem than the original misses it replaced, but worth noting.

+ +

5. The capstone prompt did not improve results

+ +
+ Capstone Prompt: No Benefit + The capstone prompt performed at or slightly below the original prompt for both models. Its emphasis on precision over recall ("do not guess") hurt overall detection rates without meaningfully improving color accuracy. +
+ + + +

6. Gemini speed improvement from concurrency

+ +

The concurrent processing optimization (8 workers + session reuse + JPEG quality 85) delivered major speed gains:

+ + + + + + + + + + + + + + + + + + + + + + +
Previous Sequential RunsCurrent Concurrent Runs
2134s (13.3s avg)253s (1.6s avg)
1882s (11.7s avg)260s (1.6s avg)
—344s (2.1s avg)
+ +

That's roughly an 8x speedup for the first two prompts. The constrained prompt run was slightly slower (344s) due to its longer prompt text (2223 chars vs ~1500 chars).

+ +
+ +

Persistently Failed Images

+ +

These 10 images failed across all six runs, representing the hardest cases for current VLMs regardless of model or prompt:

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ImageGT ColorsTypical Error
016 - maroon.jpgmaroonNot detected or called "red"
034 - light blue.jpglight blueCalled "blue"
046 - green.jpggreenCalled "black"
053 - black_white.jpgblackNot detected
077 - teal_white.jpgtealCalled "green"
132 - brown_white.jpgbrownCalled "orange"
134 - teal_white.jpgtealCalled "blue" or "light blue"
138 - maroon.jpgmaroonCalled "red"
150 - green_gray.jpggreen, grayCalled "black"
160 - blue_white.jpgblueNot detected
+ +

Notable improvements: Images 029 (maroon), 087/141/161 (light blue), and 099 (maroon) were previously persistent failures but were fixed by the constrained prompt for at least one model.

+ +
+ +

Model Comparison

+ +
+
+

Gemini 3 Flash

+
    +
  • Best at: Precision (94.3% with constrained prompt), fewest hallucinated colors
    • +
  • Weakness: Lower exact recall than Qwen; still uses shade variants even with constraints
    • +
  • Speed: ~250–340s with 8 concurrent workers
    • +
+
+
+

Qwen3-VL-8B

+
    +
  • Best at: Recall (82.7% with constrained prompt), highest PASS count (127)
    • +
  • Weakness: Higher false positive rate; introduced "maroon" overcorrection with constrained prompt
    • +
  • Speed: ~1440–1600s sequential (local GPU inference)
    • +
+
+
+ +
+ +

Recommendations

+ +
    +
  1. Use the constrained prompt (jersey_prompt_constrained.txt) — it is the clear winner for both models, improving recall and precision simultaneously.
    2. +
  2. Post-processing normalization could still recover additional matches: map grey → gray (catches any remaining Gemini outputs) and navy → navy blue (catches shorthand usage).
    3. +
  3. Consider a brown/maroon calibration — the constrained prompt overcorrected on Qwen, turning brown→maroon confusion into a new error source. Adding "Use 'brown' for warm, non-reddish dark colors" or similar guidance may help.
    4. +
  4. Gray and black detection remain unsolved at the prompt level — these are likely image quality or model perception limitations that no amount of prompt engineering will fix. These colors may benefit from a secondary computer vision pass (e.g., dominant color extraction from the jersey region).
    5. +
  5. Retire the capstone prompt — it offered no benefit over the original and performed worse than the constrained prompt in every metric.
    6. +
+ +
+ +

Appendix: Color Similarity Families Used for Scoring

+ + + + + + + + + + + + + + + + + + + + + + + +
FamilyMember Colors
blueblue, dark blue, navy blue, navy, royal blue
light_bluelight blue, sky blue, baby blue, carolina blue, powder blue
redred, scarlet, crimson
dark_redmaroon, burgundy, dark red, wine
greengreen, dark green, forest green, kelly green
yellowyellow, gold, golden
orangeorange, burnt orange
brownbrown, dark brown
purplepurple, violet
graygray, grey, silver, charcoal
blackblack
tealteal, turquoise, cyan, aqua
pinkpink, magenta, hot pink, rose
+ +
+ +

Appendix: Constrained Prompt (jersey_prompt_constrained.txt)

+ +
You are an expert at detecting sports jerseys in images. Carefully examine the provided image and identify all visible sports jerseys.
+
+CRITICAL INSTRUCTIONS:
+1. ONLY detect jerseys that are CLEARLY VISIBLE in the image
+2. ONLY include jersey numbers that you can ACTUALLY READ in the image
+3. If you CANNOT see any jerseys, you MUST return {"jerseys": []}
+4. DO NOT make up, imagine, or guess jersey numbers that aren't visible
+5. DO NOT include jerseys if you cannot clearly see the number
+
+COLOR VOCABULARY:
+For "jersey_color" and "number_color", you MUST choose from this list ONLY:
+red, blue, dark blue, navy blue, light blue, green, yellow, gold, orange, purple, black, white, gray, brown, dark brown, maroon, teal, pink
+
+Important color distinctions:
+- Use "maroon" for dark brownish-red, NOT "red"
+- Use "light blue" for pale or sky blue, NOT "blue"
+- Use "navy blue" for very dark blue, NOT "blue" or "dark blue"
+- Use "teal" for blue-green, NOT "green" or "blue"
+- Use "gray" (not "grey") for silver or neutral tones
+- Use "dark brown" for very dark brown, NOT "black"
+- Use "gold" for metallic or deep yellow, NOT "yellow"
+
+RESPONSE FORMAT:
+Respond ONLY with a valid JSON object. No explanations, no markdown, no extra text.
+
+Use DOUBLE QUOTES (") for all JSON keys and string values.
+
+The JSON must have a single key "jerseys" with an array of dictionaries.
+
+Each dictionary must have exactly these three keys:
+- "jersey_number": The number on the jersey (as a string, only if clearly visible)
+- "jersey_color": The primary color of the jersey (MUST be from the color list above)
+- "number_color": The color of the number on the jersey (MUST be from the color list above)
+
+Example response for an image WITH visible jerseys:
+{
+  "jerseys": [
+    {
+      "jersey_number": "10",
+      "jersey_color": "maroon",
+      "number_color": "gold"
+    },
+    {
+      "jersey_number": "42",
+      "jersey_color": "light blue",
+      "number_color": "white"
+    }
+  ]
+}
+
+Example response for an image WITHOUT jerseys or with unclear numbers:
+{"jerseys": []}
+
+REMEMBER: Only include jerseys with numbers you can ACTUALLY SEE in the image. When in doubt, return empty array.
+
+Now analyze the image and return the JSON object.
+ + + diff --git a/accuracy_analysis_report_round2.md b/accuracy_analysis_report_round2.md new file mode 100644 index 0000000..bb38c4a --- /dev/null +++ b/accuracy_analysis_report_round2.md @@ -0,0 +1,229 @@ +# Jersey Color Detection Accuracy — Round 2 Analysis + +**Date:** March 3, 2026 +**Models:** Gemini 3 Flash Preview, Qwen3-VL-8B (local via llama.cpp) +**Prompts:** jersey_prompt.txt (original), jersey_prompt_capstone.txt (capstone), jersey_prompt_constrained.txt (constrained) +**Test set:** 161 annotated images, 202 ground truth colors (excluding white) + +--- + +## Summary Comparison + +| Metric | Qwen Original | Qwen Capstone | Qwen Constrained | Gemini Original | Gemini Capstone | Gemini Constrained | +|----------------------------|:-------------:|:-------------:|:-----------------:|:---------------:|:---------------:|:------------------:| +| **Recall (exact)** | 65.3% | 66.3% | **71.8%** | 62.4% | 60.9% | 67.8% | +| **Recall (exact+similar)** | 78.2% | 78.2% | **82.7%** | 79.7% | 78.2% | 81.7% | +| **Missed** | 21.8% | 21.8% | **17.3%** | 20.3% | 21.8% | 18.3% | +| **Precision (exact)** | 71.7% | 74.0% | 78.4% | 72.0% | 69.5% | **78.7%** | +| **Precision (exact+sim.)** | 85.9% | 87.3% | 90.3% | 91.4% | 88.7% | **94.3%** | +| **Extra/wrong** | 14.1% | 12.7% | 9.7% | 8.6% | 11.3% | **5.7%** | +| PASS | 118 | 120 | **127** | 120 | 117 | 124 | +| PARTIAL | 19 | 19 | **15** | 20 | 22 | 19 | +| FAIL | 24 | 22 | 19 | 21 | 22 | **18** | +| Total time | 1557s | 1437s | 1596s | 253s | 260s | 344s | + +--- + +## Key Findings + +### 1. The constrained prompt is the best prompt for both models + +The constrained vocabulary prompt delivered the strongest results across the board: + +- **Qwen + Constrained** achieved the highest recall of any combination at **82.7%** (167/202 found), up from 78.2% with both other prompts. It also posted the most PASS images (**127**, up from 118/120) and the fewest FAIL images (**19**, down from 24/22). + +- **Gemini + Constrained** achieved the highest precision of any combination at **94.3%** (164/174 correct), with only **5.7% extra/wrong** colors — the lowest error rate across all six runs. It tied for fewest failures at **18**. + +### 2. Exact match rates jumped significantly + +The constrained prompt's biggest impact was converting similar matches into exact matches by forcing models to use the ground truth vocabulary: + +| Model | Exact Match (Original) | Exact Match (Constrained) | Improvement | +|--------|:----------------------:|:-------------------------:|:-----------:| +| Qwen | 65.3% (132) | **71.8% (145)** | +6.5 pp | +| Gemini | 62.4% (126) | **67.8% (137)** | +5.4 pp | + +This came partly from eliminating vocabulary mismatch (e.g., grey→gray, navy→navy blue) and partly from teaching models to use specific color terms like "maroon" and "light blue." + +### 3. Targeted color improvements + +The constrained prompt's explicit color guidance fixed the worst systematic errors: + +| Problem Color | Qwen Misses (Orig→Constrained) | Gemini Misses (Orig→Constrained) | +|----------------|:------------------------------:|:--------------------------------:| +| **maroon** | 8 → **3** | 6 → **3** | +| **light blue** | 7 → **1** | 3 → **1** | +| **dark brown** | 4 → **2** | 1 → 1 | +| **teal** | 2 → **2** | 2 → 2 | +| **gray** | 7 → 8 | 6 → 6 | +| **black** | 6 → 6 | 7 → 7 | + +- **Maroon:** Cut in half for both models. Previously the most-missed color for Qwen; now ranks 5th. +- **Light blue:** Near-elimination of the "light blue → blue" confusion for both models (7→1 for Qwen, 3→1 for Gemini). +- **Gray/grey:** The spelling normalization instruction eliminated the grey→gray similar-match penalty for Gemini entirely (10 confusions → 0). However, gray detection misses remain unchanged — these are images where gray jerseys aren't detected at all, not a naming issue. +- **Teal and black** remain stubbornly problematic regardless of prompt. + +### 4. New overcorrection pattern with constrained prompt + +The constrained prompt introduced a new failure mode — models now occasionally over-apply newly-learned color terms: + +- **Qwen + Constrained** reported "maroon" as an extra/wrong color **5 times** (was 0 previously). It's now calling some brown and red jerseys "maroon" — the opposite of the original problem. Specific cases: 007 (brown→maroon), 031 (brown→maroon), 048 (red→maroon), 142 (orange→maroon). + +- **Gemini + Constrained** reported "light blue" as an extra/wrong color **2 times** (was 0 previously), including misidentifying navy blue as light blue (image 081). + +This overcorrection is a smaller problem than the original misses it replaced, but worth noting. + +### 5. The capstone prompt did not improve results + +The capstone prompt performed at or slightly below the original prompt for both models: + +- Qwen: 78.2% recall (same), 87.3% precision (slight improvement) +- Gemini: 78.2% recall (down from 79.7%), 88.7% precision (down from 91.4%) + +The capstone prompt's emphasis on precision over recall ("do not guess") may have hurt overall detection rates without meaningfully improving color accuracy. + +### 6. Gemini speed improvement from concurrency + +The concurrent processing optimization (8 workers + session reuse + JPEG quality 85) delivered major speed gains for the Gemini runs: + +| Previous sequential runs | Current concurrent runs | +|:------------------------:|:-----------------------:| +| 2134s (13.3s avg) | 253s (1.6s avg) | +| 1882s (11.7s avg) | 260s (1.6s avg) | +| | 344s (2.1s avg) | + +That's roughly an **8x speedup** for the first two prompts. The constrained prompt run was slightly slower (344s) due to its longer prompt text (2223 chars vs ~1500 chars). + +--- + +## Persistently Failed Images + +These **10 images** failed across all six runs, representing the hardest cases for current VLMs regardless of model or prompt: + +| Image | GT Colors | Typical Error | +|-------|-----------|---------------| +| 016 - maroon.jpg | maroon | Not detected or called "red" | +| 034 - light blue.jpg | light blue | Called "blue" | +| 046 - green.jpg | green | Called "black" | +| 053 - black_white.jpg | black | Not detected | +| 077 - teal_white.jpg | teal | Called "green" | +| 132 - brown_white.jpg | brown | Called "orange" | +| 134 - teal_white.jpg | teal | Called "blue" or "light blue" | +| 138 - maroon.jpg | maroon | Called "red" | +| 150 - green_gray.jpg | green, gray | Called "black" | +| 160 - blue_white.jpg | blue | Not detected | + +Notable improvements: Images **029** (maroon), **087/141/161** (light blue), and **099** (maroon) were previously persistent failures but were **fixed by the constrained prompt** for at least one model. + +--- + +## Model Comparison + +### Gemini 3 Flash +- **Best at:** Precision (94.3% with constrained prompt), fewest hallucinated colors +- **Weakness:** Lower exact recall than Qwen; still uses shade variants even with constraints +- **Speed:** ~250-340s with 8 concurrent workers + +### Qwen3-VL-8B +- **Best at:** Recall (82.7% with constrained prompt), highest PASS count (127) +- **Weakness:** Higher false positive rate; introduced "maroon" overcorrection with constrained prompt +- **Speed:** ~1440-1600s sequential (local GPU inference) + +--- + +## Recommendations + +1. **Use the constrained prompt** (`jersey_prompt_constrained.txt`) — it is the clear winner for both models, improving recall and precision simultaneously. + +2. **Post-processing normalization** could still recover additional matches: + - Map `grey` → `gray` (catches any remaining Gemini outputs) + - Map `navy` → `navy blue` (catches shorthand usage) + +3. **Consider a brown/maroon calibration** — the constrained prompt overcorrected on Qwen, turning brown→maroon confusion into a new error source. Adding "Use 'brown' for warm, non-reddish dark colors" or similar guidance may help. + +4. **Gray and black detection remain unsolved** at the prompt level — these are likely image quality or model perception limitations that no amount of prompt engineering will fix. These colors may benefit from a secondary computer vision pass (e.g., dominant color extraction from the jersey region). + +5. **Retire the capstone prompt** — it offered no benefit over the original and performed worse than the constrained prompt in every metric. + +--- + +## Appendix: Color Similarity Families Used for Scoring + +| Family | Member Colors | +|------------|-------------------------------------------------------| +| blue | blue, dark blue, navy blue, navy, royal blue | +| light_blue | light blue, sky blue, baby blue, carolina blue, powder blue | +| red | red, scarlet, crimson | +| dark_red | maroon, burgundy, dark red, wine | +| green | green, dark green, forest green, kelly green | +| yellow | yellow, gold, golden | +| orange | orange, burnt orange | +| brown | brown, dark brown | +| purple | purple, violet | +| gray | gray, grey, silver, charcoal | +| black | black | +| teal | teal, turquoise, cyan, aqua | +| pink | pink, magenta, hot pink, rose | + +--- + +## Appendix: Constrained Prompt (`jersey_prompt_constrained.txt`) + +``` +You are an expert at detecting sports jerseys in images. Carefully examine the provided image and identify all visible sports jerseys. + +CRITICAL INSTRUCTIONS: +1. ONLY detect jerseys that are CLEARLY VISIBLE in the image +2. ONLY include jersey numbers that you can ACTUALLY READ in the image +3. If you CANNOT see any jerseys, you MUST return {"jerseys": []} +4. DO NOT make up, imagine, or guess jersey numbers that aren't visible +5. DO NOT include jerseys if you cannot clearly see the number + +COLOR VOCABULARY: +For "jersey_color" and "number_color", you MUST choose from this list ONLY: +red, blue, dark blue, navy blue, light blue, green, yellow, gold, orange, purple, black, white, gray, brown, dark brown, maroon, teal, pink + +Important color distinctions: +- Use "maroon" for dark brownish-red, NOT "red" +- Use "light blue" for pale or sky blue, NOT "blue" +- Use "navy blue" for very dark blue, NOT "blue" or "dark blue" +- Use "teal" for blue-green, NOT "green" or "blue" +- Use "gray" (not "grey") for silver or neutral tones +- Use "dark brown" for very dark brown, NOT "black" +- Use "gold" for metallic or deep yellow, NOT "yellow" + +RESPONSE FORMAT: +Respond ONLY with a valid JSON object. No explanations, no markdown, no extra text. + +Use DOUBLE QUOTES (") for all JSON keys and string values. + +The JSON must have a single key "jerseys" with an array of dictionaries. + +Each dictionary must have exactly these three keys: +- "jersey_number": The number on the jersey (as a string, only if clearly visible) +- "jersey_color": The primary color of the jersey (MUST be from the color list above) +- "number_color": The color of the number on the jersey (MUST be from the color list above) + +Example response for an image WITH visible jerseys: +{ + "jerseys": [ + { + "jersey_number": "10", + "jersey_color": "maroon", + "number_color": "gold" + }, + { + "jersey_number": "42", + "jersey_color": "light blue", + "number_color": "white" + } + ] +} + +Example response for an image WITHOUT jerseys or with unclear numbers: +{"jerseys": []} + +REMEMBER: Only include jerseys with numbers you can ACTUALLY SEE in the image. When in doubt, return empty array. + +Now analyze the image and return the JSON object. +``` diff --git a/accuracy_test_results.md b/accuracy_test_results.md new file mode 100644 index 0000000..486863f --- /dev/null +++ b/accuracy_test_results.md @@ -0,0 +1,490 @@ +#Gemini 3 Flash Results (Prompt: jersey_prompt.txt): + +================================================================================ +ACCURACY SUMMARY (gemini-3-flash-preview) +================================================================================ +Images processed: 161 +Errors: 0 +Total time: 2134.4s (13.3s avg) + +Ground truth colors: 202 (excluding white) +VLM unique colors: 174 (excluding white) + +--- Recall (did VLM find each ground truth color?) --- + Exact match: 130 / 202 (64.4%) + Similar match: 34 / 202 (16.8%) + Total found: 164 / 202 (81.2%) + Missed: 38 / 202 (18.8%) + +--- Precision (are VLM colors correct?) --- + Exact match: 130 / 174 (74.7%) + Similar match: 33 / 174 (19.0%) + Total correct: 163 / 174 (93.7%) + Extra/wrong: 11 / 174 (6.3%) + +--- Similar-Match Confusions (expected -> got) --- + gray -> grey x9 + navy blue -> blue x7 + dark brown -> brown x5 + dark blue -> blue x5 + gold -> yellow x3 + dark blue -> navy blue x3 + navy -> navy blue x1 + dark blue -> navy x1 + +--- Most Missed Ground Truth Colors --- + gray 7 ####### + black 7 ####### + maroon 5 ##### + blue 3 ### + green 3 ### + gold 2 ## + light blue 2 ## + gold|yellow 2 ## + red 2 ## + teal 2 ## + orange 1 # + yellow 1 # + brown 1 # + +--- Most Common Extra/Wrong VLM Colors --- + red 3 ### + blue 3 ### + black 2 ## + green 1 # + orange 1 # + dark blue 1 # + +--- Per-Image Verdict --- + PASS 124 + PARTIAL 19 + FAIL 18 + +--- Failed Images (18) --- + 016 - maroon.jpg + missed: maroon + 029 -maroon_white.jpg + missed: maroon + extra: red + 034 - light blue.jpg + missed: light blue + extra: blue + 046 - green.jpg + missed: green + extra: black + 048 - red.jpg + missed: red + 053 - black_white.jpg + missed: black + 057 - white_gold or yellow.jpg + missed: gold|yellow + 069 - red_white.jpg + missed: red + 074 - white_orange.jpg + missed: orange + 077 - teal_white.jpg + missed: teal + extra: green + 088 - white_maroon.jpg + missed: maroon + 129 - blue_white.jpg + missed: blue + 132 - brown_white.jpg + missed: brown + extra: orange + 134 - teal_white.jpg + missed: teal + extra: blue + 138 - maroon.jpg + missed: maroon + extra: red + 150 - green_gray.jpg + missed: green, gray + extra: black + 160 - blue_white.jpg + missed: blue + 161 - light blue_white.jpg + missed: light blue + extra: blue + + +#Qwen3-VL-8B Model Results (Prompt: jersey_prompt.txt): + +================================================================================ +ACCURACY SUMMARY +================================================================================ +Images processed: 161 +Errors: 0 +Total time: 1526.4s (9.5s avg) + +Ground truth colors: 202 (excluding white) +VLM unique colors: 184 (excluding white) + +--- Recall (did VLM find each ground truth color?) --- + Exact match: 130 / 202 (64.4%) + Similar match: 26 / 202 (12.9%) + Total found: 156 / 202 (77.2%) + Missed: 46 / 202 (22.8%) + +--- Precision (are VLM colors correct?) --- + Exact match: 130 / 184 (70.7%) + Similar match: 26 / 184 (14.1%) + Total correct: 156 / 184 (84.8%) + Extra/wrong: 28 / 184 (15.2%) + +--- Similar-Match Confusions (expected -> got) --- + dark blue -> blue x10 + navy blue -> blue x8 + gold -> yellow x5 + dark brown -> brown x2 + navy -> blue x1 + +--- Most Missed Ground Truth Colors --- + light blue 8 ######## + maroon 8 ######## + gray 7 ####### + black 6 ###### + dark brown 4 #### + brown 3 ### + blue 3 ### + green 3 ### + teal 2 ## + gold|yellow 1 # + red 1 # + +--- Most Common Extra/Wrong VLM Colors --- + blue 10 ########## + black 7 ####### + red 7 ####### + gold 1 # + green 1 # + redolas 1 # + orange 1 # + +--- Per-Image Verdict --- + PASS 117 + PARTIAL 18 + FAIL 26 + +--- Failed Images (26) --- + 001 -brown_white or dark brown.jpg + missed: brown, dark brown + extra: black + 013 - light blue.jpg + missed: light blue + extra: blue + 016 - maroon.jpg + missed: maroon + 017 - brown_white.jpg + missed: brown + extra: black + 022 - black_light blue.jpg + missed: black, light blue + extra: blue + 029 -maroon_white.jpg + missed: maroon + extra: red + 034 - light blue.jpg + missed: light blue + extra: blue + 036 - light blue_white.jpg + missed: light blue + extra: blue + 046 - green.jpg + missed: green + extra: black + 053 - black_white.jpg + missed: black + 057 - white_gold or yellow.jpg + missed: gold|yellow + 063 - dark brown.jpg + missed: dark brown + extra: black + 069 - red_white.jpg + missed: red + 077 - teal_white.jpg + missed: teal + extra: green + 078 - light blue_white.jpg + missed: light blue + extra: blue + 083 - dark brown_white.jpg + missed: dark brown + extra: black + 087 - white_light blue.jpg + missed: light blue + extra: blue + 099 - maroon_white.jpg + missed: maroon + extra: redolas, red + 129 - blue_white.jpg + missed: blue + 132 - brown_white.jpg + missed: brown + extra: orange + 134 - teal_white.jpg + missed: teal + extra: blue + 138 - maroon.jpg + missed: maroon + extra: red + 141 - light blue_white.jpg + missed: light blue + extra: blue + 150 - green_gray.jpg + missed: green, gray + extra: black + 160 - blue_white.jpg + missed: blue + 161 - light blue_white.jpg + missed: light blue + extra: blue + + +#Gemini 3 Flash Results (Prompt: jersey_prompt_capstone.txt): + +================================================================================ +ACCURACY SUMMARY (gemini-3-flash-preview) +================================================================================ +Images processed: 161 +Errors: 0 +Total time: 1881.7s (11.7s avg) + +Ground truth colors: 202 (excluding white) +VLM unique colors: 174 (excluding white) + +--- Recall (did VLM find each ground truth color?) --- + Exact match: 123 / 202 (60.9%) + Similar match: 35 / 202 (17.3%) + Total found: 158 / 202 (78.2%) + Missed: 44 / 202 (21.8%) + +--- Precision (are VLM colors correct?) --- + Exact match: 123 / 174 (70.7%) + Similar match: 34 / 174 (19.5%) + Total correct: 157 / 174 (90.2%) + Extra/wrong: 17 / 174 (9.8%) + +--- Similar-Match Confusions (expected -> got) --- + gray -> grey x10 + navy blue -> blue x6 + dark blue -> blue x6 + dark brown -> brown x5 + dark blue -> navy blue x3 + gold -> yellow x2 + navy blue -> navy x1 + navy -> blue x1 + dark blue -> navy x1 + +--- Most Missed Ground Truth Colors --- + maroon 9 ######### + black 7 ####### + gray 6 ###### + green 4 #### + gold 3 ### + blue 3 ### + light blue 2 ## + gold|yellow 2 ## + red 2 ## + teal 2 ## + navy blue 1 # + dark brown 1 # + yellow 1 # + brown 1 # + +--- Most Common Extra/Wrong VLM Colors --- + red 7 ####### + black 4 #### + blue 2 ## + green 1 # + orange 1 # + light blue 1 # + navy 1 # + +--- Per-Image Verdict --- + PASS 118 + PARTIAL 21 + FAIL 22 + +--- Failed Images (22) --- + 016 - maroon.jpg + missed: maroon + 019 - maroon_gold.jpg + missed: maroon, gold + extra: red + 029 -maroon_white.jpg + missed: maroon + extra: red + 030 - navy blue_white.jpg + missed: navy blue + 034 - light blue.jpg + missed: light blue + extra: blue + 036 - light blue_white.jpg + missed: light blue + extra: blue + 046 - green.jpg + missed: green + extra: black + 048 - red.jpg + missed: red + 053 - black_white.jpg + missed: black + 057 - white_gold or yellow.jpg + missed: gold|yellow + 069 - red_white.jpg + missed: red + 077 - teal_white.jpg + missed: teal + extra: green + 083 - dark brown_white.jpg + missed: dark brown + extra: black + 088 - white_maroon.jpg + missed: maroon + 099 - maroon_white.jpg + missed: maroon + extra: red + 128 - green_white.jpg + missed: green + 129 - blue_white.jpg + missed: blue + 132 - brown_white.jpg + missed: brown + extra: orange + 134 - teal_white.jpg + missed: teal + extra: light blue + 138 - maroon.jpg + missed: maroon + extra: red + 150 - green_gray.jpg + missed: green, gray + extra: black + 160 - blue_white.jpg + missed: blue + + +#Qwen3-VL-8B Model Results (Prompt: jersey_prompt_capstone.txt): + +================================================================================ +ACCURACY SUMMARY +================================================================================ +Images processed: 161 +Errors: 0 +Total time: 1435.7s (8.9s avg) + +Ground truth colors: 202 (excluding white) +VLM unique colors: 180 (excluding white) + +--- Recall (did VLM find each ground truth color?) --- + Exact match: 133 / 202 (65.8%) + Similar match: 24 / 202 (11.9%) + Total found: 157 / 202 (77.7%) + Missed: 45 / 202 (22.3%) + +--- Precision (are VLM colors correct?) --- + Exact match: 133 / 180 (73.9%) + Similar match: 24 / 180 (13.3%) + Total correct: 157 / 180 (87.2%) + Extra/wrong: 23 / 180 (12.8%) + +--- Similar-Match Confusions (expected -> got) --- + dark blue -> blue x9 + navy blue -> blue x8 + gold -> yellow x3 + dark brown -> brown x2 + navy -> blue x1 + dark blue -> navy x1 + +--- Most Missed Ground Truth Colors --- + gray 9 ######### + maroon 7 ####### + black 6 ###### + light blue 5 ##### + dark brown 4 #### + green 4 #### + brown 3 ### + gold 2 ## + blue 2 ## + teal 2 ## + gold|yellow 1 # + +--- Most Common Extra/Wrong VLM Colors --- + black 7 ####### + blue 6 ###### + red 6 ###### + gold 1 # + green 1 # + orange 1 # + navy 1 # + +--- Per-Image Verdict --- + PASS 119 + PARTIAL 19 + FAIL 23 + +--- Failed Images (23) --- + 001 -brown_white or dark brown.jpg + missed: brown, dark brown + extra: black + 013 - light blue.jpg + missed: light blue + extra: blue + 016 - maroon.jpg + missed: maroon + 017 - brown_white.jpg + missed: brown + extra: black + 019 - maroon_gold.jpg + missed: maroon, gold + extra: red + 029 -maroon_white.jpg + missed: maroon + extra: red + 034 - light blue.jpg + missed: light blue + extra: blue + 036 - light blue_white.jpg + missed: light blue + extra: blue + 039 - gray_white.jpg + missed: gray + 046 - green.jpg + missed: green + extra: black + 053 - black_white.jpg + missed: black + 057 - white_gold or yellow.jpg + missed: gold|yellow + 063 - dark brown.jpg + missed: dark brown + extra: black + 077 - teal_white.jpg + missed: teal + extra: green + 083 - dark brown_white.jpg + missed: dark brown + extra: black + 132 - brown_white.jpg + missed: brown + extra: orange + 134 - teal_white.jpg + missed: teal + extra: blue + 138 - maroon.jpg + missed: maroon + extra: red + 141 - light blue_white.jpg + missed: light blue + extra: blue + 145 - green_white.jpg + missed: green + 150 - green_gray.jpg + missed: green, gray + extra: black + 160 - blue_white.jpg + missed: blue + 161 - light blue_white.jpg + missed: light blue + extra: blue diff --git a/accuracy_test_results_all.txt b/accuracy_test_results_all.txt new file mode 100644 index 0000000..3d163c9 --- /dev/null +++ b/accuracy_test_results_all.txt @@ -0,0 +1,5609 @@ +======================================== +Qwen3-VL-8B + jersey_prompt.txt +Started: Tue Mar 3 04:40:45 PM MST 2026 +======================================== +Images to process: 161 +Server: http://agx:8080 +Prompt: /home/rmcewen/data/dev.python/jersey_test/jersey_prompt.txt (1504 chars) +================================================================================ + +[1/161] 001 -brown_white or dark brown.jpg + GT: [brown, dark brown] + VLM: [black] (3 jersey(s), 11.1s) + FAIL MISS:brown,dark brown, extra:black + +[2/161] 002 - yellow.jpg + GT: [yellow] + VLM: [yellow] (2 jersey(s), 7.9s) + PASS exact:1 + +[3/161] 003 - dark blue.jpg + GT: [dark blue] + VLM: [blue] (3 jersey(s), 10.8s) + PASS similar:1 + +[4/161] 004 - purple_light blue.jpg + GT: [purple, light blue] + VLM: [light blue, purple] (3 jersey(s), 11.9s) + PASS exact:2 + +[5/161] 005 - white or gray_purple.jpg + GT: [gray, purple] + VLM: [purple] (1 jersey(s), 5.0s) + PARTIAL exact:1, MISS:gray + +[6/161] 006 - navy blue.jpg + GT: [navy blue] + VLM: [blue] (1 jersey(s), 4.3s) + PASS similar:1 + +[7/161] 007 - brown_white.jpg + GT: [brown] + VLM: [brown] (2 jersey(s), 7.9s) + PASS exact:1 + +[8/161] 008 -red or orange.jpg + GT: [red|orange] + VLM: [red] (1 jersey(s), 4.3s) + PASS exact:1 + +[9/161] 009 - white_red.jpg + GT: [red] + VLM: [gold, red] (3 jersey(s), 10.8s) + PARTIAL exact:1, extra:gold + +[10/161] 010 - white_black.jpg + GT: [black] + VLM: [black] (3 jersey(s), 10.9s) + PASS exact:1 + +[11/161] 011 - white or gray_purple.jpg + GT: [gray, purple] + VLM: [purple] (4 jersey(s), 13.8s) + PARTIAL exact:1, MISS:gray + +[12/161] 012 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 7.3s) + PASS exact:1 + +[13/161] 013 - light blue.jpg + GT: [light blue] + VLM: [blue] (2 jersey(s), 7.5s) + FAIL MISS:light blue, extra:blue + +[14/161] 014 - orange_dark blue or purple.jpg + GT: [orange, dark blue|purple] + VLM: [orange, purple] (3 jersey(s), 10.9s) + PASS exact:2 + +[15/161] 015 - green.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.3s) + PASS exact:1 + +[16/161] 016 - maroon.jpg + GT: [maroon] + VLM: [(none)] (0 jersey(s), 1.5s) + FAIL MISS:maroon + +[17/161] 017 - brown_white.jpg + GT: [brown] + VLM: [black] (2 jersey(s), 8.8s) + FAIL MISS:brown, extra:black + +[18/161] 018 - gray_red.jpg + GT: [gray, red] + VLM: [gray, red] (2 jersey(s), 7.4s) + PASS exact:2 + +[19/161] 019 - maroon_gold.jpg + GT: [maroon, gold] + VLM: [red, yellow] (2 jersey(s), 7.7s) + PARTIAL similar:1, MISS:maroon, extra:red + +[20/161] 020 - white_brown or orange.jpg + GT: [brown|orange] + VLM: [orange] (2 jersey(s), 8.1s) + PASS exact:1 + +[21/161] 021 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 7.9s) + PASS exact:1 + +[22/161] 022 - black_light blue.jpg + GT: [black, light blue] + VLM: [light blue] (1 jersey(s), 4.9s) + PARTIAL exact:1, MISS:black + +[23/161] 023 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 7.8s) + PASS exact:1 + +[24/161] 024 - white_pink.jpg + GT: [pink] + VLM: [pink] (2 jersey(s), 7.8s) + PASS exact:1 + +[25/161] 025 - blue_green.jpg + GT: [blue, green] + VLM: [green] (1 jersey(s), 4.3s) + PARTIAL exact:1, MISS:blue + +[26/161] 026 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.9s) + PASS exact:1 + +[27/161] 027 - red_white.jpg + GT: [red] + VLM: [red] (5 jersey(s), 16.3s) + PASS exact:1 + +[28/161] 028 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.8s) + PASS exact:1 + +[29/161] 029 -maroon_white.jpg + GT: [maroon] + VLM: [red] (2 jersey(s), 7.8s) + FAIL MISS:maroon, extra:red + +[30/161] 030 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (2 jersey(s), 7.8s) + PASS similar:1 + +[31/161] 031 - brown_white.jpg + GT: [brown] + VLM: [brown] (2 jersey(s), 7.8s) + PASS exact:1 + +[32/161] 032 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 8.0s) + PASS exact:1 + +[33/161] 033 - navy blue_white or gray.jpg + GT: [navy blue, gray] + VLM: [blue] (3 jersey(s), 10.9s) + PARTIAL similar:1, MISS:gray + +[34/161] 034 - light blue.jpg + GT: [light blue] + VLM: [blue] (1 jersey(s), 4.7s) + FAIL MISS:light blue, extra:blue + +[35/161] 035 -green_gold or yellow.jpg + GT: [green, gold|yellow] + VLM: [green, yellow] (2 jersey(s), 8.1s) + PASS exact:2 + +[36/161] 036 - light blue_white.jpg + GT: [light blue] + VLM: [blue] (4 jersey(s), 13.7s) + FAIL MISS:light blue, extra:blue + +[37/161] 037 -navy_white.jpg + GT: [navy] + VLM: [blue] (3 jersey(s), 10.1s) + PASS similar:1 + +[38/161] 038 - red_white.jpg + GT: [red] + VLM: [red] (3 jersey(s), 10.9s) + PASS exact:1 + +[39/161] 039 - gray_white.jpg + GT: [gray] + VLM: [gray] (2 jersey(s), 7.9s) + PASS exact:1 + +[40/161] 040 - maroon_gray.jpg + GT: [maroon, gray] + VLM: [maroon] (1 jersey(s), 5.1s) + PARTIAL exact:1, MISS:gray + +[41/161] 041 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (8 jersey(s), 25.7s) + PASS similar:1 + +[42/161] 042 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 4.8s) + PASS exact:1 + +[43/161] 043 - gray_black.jpg + GT: [gray, black] + VLM: [black, gray] (2 jersey(s), 7.9s) + PASS exact:2 + +[44/161] 044 - purple_black.jpg + GT: [purple, black] + VLM: [purple] (5 jersey(s), 16.6s) + PARTIAL exact:1, MISS:black + +[45/161] 045 - purple.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 7.8s) + PASS exact:1 + +[46/161] 046 - green.jpg + GT: [green] + VLM: [black] (15 jersey(s), 46.4s) + FAIL MISS:green, extra:black + +[47/161] 047 - purple_white.jpg + GT: [purple] + VLM: [purple] (3 jersey(s), 10.7s) + PASS exact:1 + +[48/161] 048 - red.jpg + GT: [red] + VLM: [red] (1 jersey(s), 4.9s) + PASS exact:1 + +[49/161] 049 - white_gold.jpg + GT: [gold] + VLM: [yellow] (2 jersey(s), 7.9s) + PASS similar:1 + +[50/161] 050 - white_orange.jpg + GT: [orange] + VLM: [orange] (4 jersey(s), 13.8s) + PASS exact:1 + +[51/161] 051 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 4.9s) + PASS exact:1 + +[52/161] 052 - black_gold.jpg + GT: [black, gold] + VLM: [black, yellow] (2 jersey(s), 7.8s) + PASS exact:1, similar:1 + +[53/161] 053 - black_white.jpg + GT: [black] + VLM: [(none)] (1 jersey(s), 4.9s) + FAIL MISS:black + +[54/161] 054 - white_blue.jpg + GT: [blue] + VLM: [blue] (2 jersey(s), 7.7s) + PASS exact:1 + +[55/161] 055 - green_gold.jpg + GT: [green, gold] + VLM: [green, yellow] (2 jersey(s), 7.8s) + PASS exact:1, similar:1 + +[56/161] 056 - white_red.jpg + GT: [red] + VLM: [red] (2 jersey(s), 7.9s) + PASS exact:1 + +[57/161] 057 - white_gold or yellow.jpg + GT: [gold|yellow] + VLM: [yellow] (2 jersey(s), 7.9s) + PASS exact:1 + +[58/161] 058 - purple.jpg + GT: [purple] + VLM: [purple] (4 jersey(s), 14.0s) + PASS exact:1 + +[59/161] 059 - black_gold.jpg + GT: [black, gold] + VLM: [gold] (1 jersey(s), 4.9s) + PARTIAL exact:1, MISS:black + +[60/161] 060 - gray_navy blue.jpg + GT: [gray, navy blue] + VLM: [blue] (2 jersey(s), 7.9s) + PARTIAL similar:1, MISS:gray + +[61/161] 061 - brown or orange.jpg + GT: [brown|orange] + VLM: [orange] (2 jersey(s), 7.9s) + PASS exact:1 + +[62/161] 062 - orange_blue.jpg + GT: [orange, blue] + VLM: [blue, orange] (2 jersey(s), 7.5s) + PASS exact:2 + +[63/161] 063 - dark brown.jpg + GT: [dark brown] + VLM: [black] (1 jersey(s), 4.9s) + FAIL MISS:dark brown, extra:black + +[64/161] 064 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.7s) + PASS exact:1 + +[65/161] 065 - green_gold.jpg + GT: [green, gold] + VLM: [green, yellow] (3 jersey(s), 10.4s) + PASS exact:1, similar:1 + +[66/161] 066 - yellow.jpg + GT: [yellow] + VLM: [yellow] (1 jersey(s), 4.7s) + PASS exact:1 + +[67/161] 067 - red_white.jpg + GT: [red] + VLM: [red] (4 jersey(s), 13.8s) + PASS exact:1 + +[68/161] 068 - gold.jpg + GT: [gold] + VLM: [gold] (1 jersey(s), 4.8s) + PASS exact:1 + +[69/161] 069 - red_white.jpg + GT: [red] + VLM: [(none)] (4 jersey(s), 13.7s) + FAIL MISS:red + +[70/161] 070 - green_white.jpg + GT: [green] + VLM: [green] (3 jersey(s), 10.8s) + PASS exact:1 + +[71/161] 071 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 7.9s) + PASS exact:1 + +[72/161] 072 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 7.5s) + PASS exact:1 + +[73/161] 073 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 7.4s) + PASS exact:1 + +[74/161] 074 - white_orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 7.5s) + PASS exact:1 + +[75/161] 075 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.8s) + PASS exact:1 + +[76/161] 076 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (3 jersey(s), 11.4s) + PASS exact:1 + +[77/161] 077 - teal_white.jpg + GT: [teal] + VLM: [green] (4 jersey(s), 13.4s) + FAIL MISS:teal, extra:green + +[78/161] 078 - light blue_white.jpg + GT: [light blue] + VLM: [blue] (2 jersey(s), 7.6s) + FAIL MISS:light blue, extra:blue + +[79/161] 079 - blue_maroon.jpg + GT: [blue, maroon] + VLM: [blue, red] (4 jersey(s), 13.8s) + PARTIAL exact:1, MISS:maroon, extra:red + +[80/161] 080 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (2 jersey(s), 7.8s) + PASS similar:1 + +[81/161] 081 - navy blue.jpg + GT: [navy blue] + VLM: [blue] (2 jersey(s), 7.8s) + PASS similar:1 + +[82/161] 082 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (3 jersey(s), 10.6s) + PASS similar:1 + +[83/161] 083 - dark brown_white.jpg + GT: [dark brown] + VLM: [black] (2 jersey(s), 7.8s) + FAIL MISS:dark brown, extra:black + +[84/161] 084 - dark brown_yellow.jpg + GT: [dark brown, yellow] + VLM: [black, yellow] (2 jersey(s), 7.9s) + PARTIAL exact:1, MISS:dark brown, extra:black + +[85/161] 085 - green_white.jpg + GT: [green] + VLM: [green] (1 jersey(s), 4.8s) + PASS exact:1 + +[86/161] 086 - dark brown_white.jpg + GT: [dark brown] + VLM: [brown] (2 jersey(s), 8.0s) + PASS similar:1 + +[87/161] 087 - white_light blue.jpg + GT: [light blue] + VLM: [blue] (2 jersey(s), 7.8s) + FAIL MISS:light blue, extra:blue + +[88/161] 088 - white_maroon.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 7.9s) + PASS exact:1 + +[89/161] 089 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 10.8s) + PASS exact:1 + +[90/161] 090 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (4 jersey(s), 14.2s) + PASS exact:1 + +[91/161] 091 - teal.jpg + GT: [teal] + VLM: [teal] (2 jersey(s), 8.0s) + PASS exact:1 + +[92/161] 092 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 13.7s) + PASS exact:1 + +[93/161] 093 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (2 jersey(s), 7.9s) + PASS similar:1 + +[94/161] 094 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 12.5s) + PASS exact:1 + +[95/161] 095 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.9s) + PASS exact:1 + +[96/161] 096 - orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 8.6s) + PASS exact:1 + +[97/161] 097 - gray_black.jpg + GT: [gray, black] + VLM: [gray] (2 jersey(s), 8.0s) + PARTIAL exact:1, MISS:black + +[98/161] 098 - teal_white.jpg + GT: [teal] + VLM: [teal] (2 jersey(s), 8.7s) + PASS exact:1 + +[99/161] 099 - maroon_white.jpg + GT: [maroon] + VLM: [red] (3 jersey(s), 12.0s) + FAIL MISS:maroon, extra:red + +[100/161] 100 - orange_white.jpg + GT: [orange] + VLM: [orange] (4 jersey(s), 13.9s) + PASS exact:1 + +[101/161] 101 - green_white.jpg + GT: [green] + VLM: [green] (5 jersey(s), 17.0s) + PASS exact:1 + +[102/161] 102 - yellow-black.jpg + GT: [yellow, black] + VLM: [black, yellow] (3 jersey(s), 10.9s) + PASS exact:2 + +[103/161] 103 - green_white.jpg + GT: [green] + VLM: [green] (3 jersey(s), 11.1s) + PASS exact:1 + +[104/161] 104 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 8.0s) + PASS exact:1 + +[105/161] 105 - orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 9.1s) + PASS exact:1 + +[106/161] 106 - black_gray.jpg + GT: [black, gray] + VLM: [black, gray] (2 jersey(s), 9.0s) + PASS exact:2 + +[107/161] 107 - orange_white.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 7.7s) + PASS exact:1 + +[108/161] 108 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 7.9s) + PASS exact:1 + +[109/161] 109 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 7.8s) + PASS exact:1 + +[110/161] 110 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 13.9s) + PASS exact:1 + +[111/161] 111 - orange_white.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 8.0s) + PASS exact:1 + +[112/161] 112 - orange_white.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 7.8s) + PASS exact:1 + +[113/161] 113 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 4.9s) + PASS exact:1 + +[114/161] 114 - black_white.jpg + GT: [black] + VLM: [black] (2 jersey(s), 8.2s) + PASS exact:1 + +[115/161] 115 - navy blue_maroon.jpg + GT: [navy blue, maroon] + VLM: [blue, red] (4 jersey(s), 13.8s) + PARTIAL similar:1, MISS:maroon, extra:red + +[116/161] 116 - gray_white.jpg + GT: [gray] + VLM: [gray] (2 jersey(s), 7.9s) + PASS exact:1 + +[117/161] 117 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 8.1s) + PASS exact:1 + +[118/161] 118 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (2 jersey(s), 7.4s) + PASS similar:1 + +[119/161] 119 - black_yellow.jpg + GT: [black, yellow] + VLM: [black, yellow] (3 jersey(s), 10.9s) + PASS exact:2 + +[120/161] 120 - red_dark blue.jpg + GT: [red, dark blue] + VLM: [blue, red] (3 jersey(s), 10.7s) + PASS exact:1, similar:1 + +[121/161] 121 - orange_white.jpg + GT: [orange] + VLM: [orange] (3 jersey(s), 10.9s) + PASS exact:1 + +[122/161] 122 - gray.jpg + GT: [gray] + VLM: [gray] (1 jersey(s), 6.2s) + PASS exact:1 + +[123/161] 123 - teal_white.jpg + GT: [teal] + VLM: [teal] (3 jersey(s), 10.9s) + PASS exact:1 + +[124/161] 124 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (4 jersey(s), 13.7s) + PASS similar:1 + +[125/161] 125 - dark blue_maroon.jpg + GT: [dark blue, maroon] + VLM: [blue, red] (2 jersey(s), 8.2s) + PARTIAL similar:1, MISS:maroon, extra:red + +[126/161] 126 - white_blue.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 10.8s) + PASS exact:1 + +[127/161] 127 - yellow.jpg + GT: [yellow] + VLM: [yellow] (4 jersey(s), 14.0s) + PASS exact:1 + +[128/161] 128 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.9s) + PASS exact:1 + +[129/161] 129 - blue_white.jpg + GT: [blue] + VLM: [(none)] (3 jersey(s), 10.9s) + FAIL MISS:blue + +[130/161] 130 - yellow_black.jpg + GT: [yellow, black] + VLM: [black, yellow] (2 jersey(s), 8.4s) + PASS exact:2 + +[131/161] 131 - purple_orange.jpg + GT: [purple, orange] + VLM: [orange, purple] (3 jersey(s), 10.8s) + PASS exact:2 + +[132/161] 132 - brown_white.jpg + GT: [brown] + VLM: [orange] (3 jersey(s), 10.9s) + FAIL MISS:brown, extra:orange + +[133/161] 133 - light blue.png + GT: [light blue] + VLM: [light blue] (6 jersey(s), 21.1s) + PASS exact:1 + +[134/161] 134 - teal_white.jpg + GT: [teal] + VLM: [blue] (1 jersey(s), 4.9s) + FAIL MISS:teal, extra:blue + +[135/161] 135 - green.jpg + GT: [green] + VLM: [green] (2 jersey(s), 8.0s) + PASS exact:1 + +[136/161] 136 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 8.1s) + PASS exact:1 + +[137/161] 137 - green_white.jpg + GT: [green] + VLM: [green] (3 jersey(s), 10.9s) + PASS exact:1 + +[138/161] 138 - maroon.jpg + GT: [maroon] + VLM: [red] (1 jersey(s), 4.9s) + FAIL MISS:maroon, extra:red + +[139/161] 139 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (2 jersey(s), 8.0s) + PASS similar:1 + +[140/161] 140 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 7.6s) + PASS exact:1 + +[141/161] 141 - light blue_white.jpg + GT: [light blue] + VLM: [blue] (3 jersey(s), 11.1s) + FAIL MISS:light blue, extra:blue + +[142/161] 142 - orange_white.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 8.1s) + PASS exact:1 + +[143/161] 143 - blue_white.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 11.0s) + PASS exact:1 + +[144/161] 144 - green.jpg + GT: [green] + VLM: [green] (10 jersey(s), 31.9s) + PASS exact:1 + +[145/161] 145 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.9s) + PASS exact:1 + +[146/161] 146 - red_gray.jpg + GT: [red, gray] + VLM: [gray, red] (2 jersey(s), 8.0s) + PASS exact:2 + +[147/161] 147 - green.jpg + GT: [green] + VLM: [green] (3 jersey(s), 10.8s) + PASS exact:1 + +[148/161] 148 - yellow_purple.jpg + GT: [yellow, purple] + VLM: [purple, yellow] (2 jersey(s), 7.9s) + PASS exact:2 + +[149/161] 149 - blue_white.jpg + GT: [blue] + VLM: [blue] (5 jersey(s), 16.7s) + PASS exact:1 + +[150/161] 150 - green_gray.jpg + GT: [green, gray] + VLM: [black] (2 jersey(s), 7.8s) + FAIL MISS:green,gray, extra:black + +[151/161] 151 - yellow_black.jpg + GT: [yellow, black] + VLM: [blue, yellow] (5 jersey(s), 16.7s) + PARTIAL exact:1, MISS:black, extra:blue + +[152/161] 152 - pink_dark blue.jpg + GT: [pink, dark blue] + VLM: [blue, pink] (2 jersey(s), 7.8s) + PASS exact:1, similar:1 + +[153/161] 153 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 8.0s) + PASS exact:1 + +[154/161] 154 - dark brown.jpeg + GT: [dark brown] + VLM: [brown] (5 jersey(s), 16.8s) + PASS similar:1 + +[155/161] 155 - white_green_gray_purple_yellow.jpg + GT: [green, gray, purple, yellow] + VLM: [gray, purple, yellow] (5 jersey(s), 17.3s) + PARTIAL exact:3, MISS:green + +[156/161] 156 - maroon_gray.jpg + GT: [maroon, gray] + VLM: [maroon] (2 jersey(s), 7.7s) + PARTIAL exact:1, MISS:gray + +[157/161] 157 - blue_white.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 10.7s) + PASS exact:1 + +[158/161] 158 - dark blue_yellow.jpg + GT: [dark blue, yellow] + VLM: [blue, yellow] (4 jersey(s), 14.0s) + PASS exact:1, similar:1 + +[159/161] 159 - blue_white.jpg + GT: [blue] + VLM: [blue] (4 jersey(s), 13.9s) + PASS exact:1 + +[160/161] 160 - blue_white.jpg + GT: [blue] + VLM: [(none)] (1 jersey(s), 4.9s) + FAIL MISS:blue + +[161/161] 161 - light blue_white.jpg + GT: [light blue] + VLM: [blue] (2 jersey(s), 7.7s) + FAIL MISS:light blue, extra:blue + +================================================================================ +ACCURACY SUMMARY +================================================================================ +Images processed: 161 +Errors: 0 +Total time: 1557.4s (9.7s avg) + +Ground truth colors: 202 (excluding white) +VLM unique colors: 184 (excluding white) + +--- Recall (did VLM find each ground truth color?) --- + Exact match: 132 / 202 (65.3%) + Similar match: 26 / 202 (12.9%) + Total found: 158 / 202 (78.2%) + Missed: 44 / 202 (21.8%) + +--- Precision (are VLM colors correct?) --- + Exact match: 132 / 184 (71.7%) + Similar match: 26 / 184 (14.1%) + Total correct: 158 / 184 (85.9%) + Extra/wrong: 26 / 184 (14.1%) + +--- Similar-Match Confusions (expected -> got) --- + dark blue -> blue x10 + navy blue -> blue x8 + gold -> yellow x5 + dark brown -> brown x2 + navy -> blue x1 + +--- Most Missed Ground Truth Colors --- + maroon 8 ######## + gray 7 ####### + light blue 7 ####### + black 6 ###### + dark brown 4 #### + brown 3 ### + blue 3 ### + green 3 ### + teal 2 ## + red 1 # + +--- Most Common Extra/Wrong VLM Colors --- + blue 9 ######### + black 7 ####### + red 7 ####### + gold 1 # + green 1 # + orange 1 # + +--- Per-Image Verdict --- + PASS 118 + PARTIAL 19 + FAIL 24 + +--- Failed Images (24) --- + 001 -brown_white or dark brown.jpg + missed: brown, dark brown + extra: black + 013 - light blue.jpg + missed: light blue + extra: blue + 016 - maroon.jpg + missed: maroon + 017 - brown_white.jpg + missed: brown + extra: black + 029 -maroon_white.jpg + missed: maroon + extra: red + 034 - light blue.jpg + missed: light blue + extra: blue + 036 - light blue_white.jpg + missed: light blue + extra: blue + 046 - green.jpg + missed: green + extra: black + 053 - black_white.jpg + missed: black + 063 - dark brown.jpg + missed: dark brown + extra: black + 069 - red_white.jpg + missed: red + 077 - teal_white.jpg + missed: teal + extra: green + 078 - light blue_white.jpg + missed: light blue + extra: blue + 083 - dark brown_white.jpg + missed: dark brown + extra: black + 087 - white_light blue.jpg + missed: light blue + extra: blue + 099 - maroon_white.jpg + missed: maroon + extra: red + 129 - blue_white.jpg + missed: blue + 132 - brown_white.jpg + missed: brown + extra: orange + 134 - teal_white.jpg + missed: teal + extra: blue + 138 - maroon.jpg + missed: maroon + extra: red + 141 - light blue_white.jpg + missed: light blue + extra: blue + 150 - green_gray.jpg + missed: green, gray + extra: black + 160 - blue_white.jpg + missed: blue + 161 - light blue_white.jpg + missed: light blue + extra: blue + +======================================== +Gemini 3 Flash + jersey_prompt.txt +Started: Tue Mar 3 05:06:43 PM MST 2026 +======================================== +Model: gemini-3-flash-preview +Images to process: 161 +Concurrency: 8 workers +Prompt: /home/rmcewen/data/dev.python/jersey_test/jersey_prompt.txt (1504 chars) +================================================================================ +Pre-encoding images ... 161 images in 1.7s +Sending API requests ... + 1/161 API calls completed 2/161 API calls completed 3/161 API calls completed 4/161 API calls completed 5/161 API calls completed 6/161 API calls completed 7/161 API calls completed 8/161 API calls completed 9/161 API calls completed 10/161 API calls completed 11/161 API calls completed 12/161 API calls completed 13/161 API calls completed 14/161 API calls completed 15/161 API calls completed 16/161 API calls completed 17/161 API calls completed 18/161 API calls completed 19/161 API calls completed 20/161 API calls completed 21/161 API calls completed 22/161 API calls completed 23/161 API calls completed 24/161 API calls completed 25/161 API calls completed 26/161 API calls completed 27/161 API calls completed 28/161 API calls completed 29/161 API calls completed 30/161 API calls completed 31/161 API calls completed 32/161 API calls completed 33/161 API calls completed 34/161 API calls completed 35/161 API calls completed 36/161 API calls completed 37/161 API calls completed 38/161 API calls completed 39/161 API calls completed 40/161 API calls completed 41/161 API calls completed 42/161 API calls completed 43/161 API calls completed 44/161 API calls completed 45/161 API calls completed 46/161 API calls completed 47/161 API calls completed 48/161 API calls completed 49/161 API calls completed 50/161 API calls completed 51/161 API calls completed 52/161 API calls completed 53/161 API calls completed 54/161 API calls completed 55/161 API calls completed 56/161 API calls completed 57/161 API calls completed 58/161 API calls completed 59/161 API calls completed 60/161 API calls completed 61/161 API calls completed 62/161 API calls completed 63/161 API calls completed 64/161 API calls completed 65/161 API calls completed 66/161 API calls completed 67/161 API calls completed 68/161 API calls completed 69/161 API calls completed 70/161 API calls completed 71/161 API calls completed 72/161 API calls completed 73/161 API calls completed 74/161 API calls completed 75/161 API calls completed 76/161 API calls completed 77/161 API calls completed 78/161 API calls completed 79/161 API calls completed 80/161 API calls completed 81/161 API calls completed 82/161 API calls completed 83/161 API calls completed 84/161 API calls completed 85/161 API calls completed 86/161 API calls completed 87/161 API calls completed 88/161 API calls completed 89/161 API calls completed 90/161 API calls completed 91/161 API calls completed 92/161 API calls completed 93/161 API calls completed 94/161 API calls completed 95/161 API calls completed 96/161 API calls completed 97/161 API calls completed 98/161 API calls completed 99/161 API calls completed 100/161 API calls completed 101/161 API calls completed 102/161 API calls completed 103/161 API calls completed 104/161 API calls completed 105/161 API calls completed 106/161 API calls completed 107/161 API calls completed 108/161 API calls completed 109/161 API calls completed 110/161 API calls completed 111/161 API calls completed 112/161 API calls completed 113/161 API calls completed 114/161 API calls completed 115/161 API calls completed 116/161 API calls completed 117/161 API calls completed 118/161 API calls completed 119/161 API calls completed 120/161 API calls completed 121/161 API calls completed 122/161 API calls completed 123/161 API calls completed 124/161 API calls completed 125/161 API calls completed 126/161 API calls completed 127/161 API calls completed 128/161 API calls completed 129/161 API calls completed 130/161 API calls completed 131/161 API calls completed 132/161 API calls completed 133/161 API calls completed 134/161 API calls completed 135/161 API calls completed 136/161 API calls completed 137/161 API calls completed 138/161 API calls completed 139/161 API calls completed 140/161 API calls completed 141/161 API calls completed 142/161 API calls completed 143/161 API calls completed 144/161 API calls completed 145/161 API calls completed 146/161 API calls completed 147/161 API calls completed 148/161 API calls completed 149/161 API calls completed 150/161 API calls completed 151/161 API calls completed 152/161 API calls completed 153/161 API calls completed 154/161 API calls completed 155/161 API calls completed 156/161 API calls completed 157/161 API calls completed 158/161 API calls completed 159/161 API calls completed 160/161 API calls completed 161/161 API calls completed (253.2s total) +================================================================================ + +[1/161] 001 -brown_white or dark brown.jpg + GT: [brown, dark brown] + VLM: [brown] (1 jersey(s), 9.0s) + PASS exact:1, similar:1 + +[2/161] 002 - yellow.jpg + GT: [yellow] + VLM: [yellow] (2 jersey(s), 6.6s) + PASS exact:1 + +[3/161] 003 - dark blue.jpg + GT: [dark blue] + VLM: [navy blue] (3 jersey(s), 9.4s) + PASS similar:1 + +[4/161] 004 - purple_light blue.jpg + GT: [purple, light blue] + VLM: [light blue, purple] (2 jersey(s), 10.5s) + PASS exact:2 + +[5/161] 005 - white or gray_purple.jpg + GT: [gray, purple] + VLM: [purple] (1 jersey(s), 3.0s) + PARTIAL exact:1, MISS:gray + +[6/161] 006 - navy blue.jpg + GT: [navy blue] + VLM: [dark blue] (1 jersey(s), 3.1s) + PASS similar:1 + +[7/161] 007 - brown_white.jpg + GT: [brown] + VLM: [brown] (2 jersey(s), 6.0s) + PASS exact:1 + +[8/161] 008 -red or orange.jpg + GT: [red|orange] + VLM: [red] (1 jersey(s), 5.1s) + PASS exact:1 + +[9/161] 009 - white_red.jpg + GT: [red] + VLM: [red] (4 jersey(s), 17.9s) + PASS exact:1 + +[10/161] 010 - white_black.jpg + GT: [black] + VLM: [black] (3 jersey(s), 11.3s) + PASS exact:1 + +[11/161] 011 - white or gray_purple.jpg + GT: [gray, purple] + VLM: [purple] (4 jersey(s), 8.5s) + PARTIAL exact:1, MISS:gray + +[12/161] 012 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 3.8s) + PASS exact:1 + +[13/161] 013 - light blue.jpg + GT: [light blue] + VLM: [blue] (2 jersey(s), 10.2s) + FAIL MISS:light blue, extra:blue + +[14/161] 014 - orange_dark blue or purple.jpg + GT: [orange, dark blue|purple] + VLM: [orange, purple] (3 jersey(s), 6.1s) + PASS exact:2 + +[15/161] 015 - green.jpg + GT: [green] + VLM: [green] (2 jersey(s), 3.4s) + PASS exact:1 + +[16/161] 016 - maroon.jpg + GT: [maroon] + VLM: [(none)] (0 jersey(s), 3.2s) + FAIL MISS:maroon + +[17/161] 017 - brown_white.jpg + GT: [brown] + VLM: [brown] (2 jersey(s), 4.8s) + PASS exact:1 + +[18/161] 018 - gray_red.jpg + GT: [gray, red] + VLM: [grey] (1 jersey(s), 6.5s) + PARTIAL similar:1, MISS:red + +[19/161] 019 - maroon_gold.jpg + GT: [maroon, gold] + VLM: [maroon] (1 jersey(s), 4.4s) + PARTIAL exact:1, MISS:gold + +[20/161] 020 - white_brown or orange.jpg + GT: [brown|orange] + VLM: [orange] (2 jersey(s), 5.6s) + PASS exact:1 + +[21/161] 021 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 7.8s) + PASS exact:1 + +[22/161] 022 - black_light blue.jpg + GT: [black, light blue] + VLM: [light blue] (1 jersey(s), 3.3s) + PARTIAL exact:1, MISS:black + +[23/161] 023 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 5.7s) + PASS exact:1 + +[24/161] 024 - white_pink.jpg + GT: [pink] + VLM: [pink] (2 jersey(s), 5.1s) + PASS exact:1 + +[25/161] 025 - blue_green.jpg + GT: [blue, green] + VLM: [green] (1 jersey(s), 3.7s) + PARTIAL exact:1, MISS:blue + +[26/161] 026 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 6.8s) + PASS exact:1 + +[27/161] 027 - red_white.jpg + GT: [red] + VLM: [red] (4 jersey(s), 35.2s) + PASS exact:1 + +[28/161] 028 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 37.9s) + PASS exact:1 + +[29/161] 029 -maroon_white.jpg + GT: [maroon] + VLM: [red] (2 jersey(s), 4.8s) + FAIL MISS:maroon, extra:red + +[30/161] 030 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (2 jersey(s), 38.6s) + PASS similar:1 + +[31/161] 031 - brown_white.jpg + GT: [brown] + VLM: [brown] (2 jersey(s), 4.9s) + PASS exact:1 + +[32/161] 032 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 5.3s) + PASS exact:1 + +[33/161] 033 - navy blue_white or gray.jpg + GT: [navy blue, gray] + VLM: [blue] (5 jersey(s), 37.0s) + PARTIAL similar:1, MISS:gray + +[34/161] 034 - light blue.jpg + GT: [light blue] + VLM: [blue] (6 jersey(s), 15.9s) + FAIL MISS:light blue, extra:blue + +[35/161] 035 -green_gold or yellow.jpg + GT: [green, gold|yellow] + VLM: [green, yellow] (2 jersey(s), 14.4s) + PASS exact:2 + +[36/161] 036 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (4 jersey(s), 6.4s) + PASS exact:1 + +[37/161] 037 -navy_white.jpg + GT: [navy] + VLM: [navy blue] (4 jersey(s), 8.3s) + PASS similar:1 + +[38/161] 038 - red_white.jpg + GT: [red] + VLM: [red] (3 jersey(s), 8.2s) + PASS exact:1 + +[39/161] 039 - gray_white.jpg + GT: [gray] + VLM: [grey] (2 jersey(s), 4.6s) + PASS similar:1 + +[40/161] 040 - maroon_gray.jpg + GT: [maroon, gray] + VLM: [grey, maroon] (2 jersey(s), 7.3s) + PASS exact:1, similar:1 + +[41/161] 041 - navy blue_white.jpg + GT: [navy blue] + VLM: [navy blue] (8 jersey(s), 42.8s) + PASS exact:1 + +[42/161] 042 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 3.0s) + PASS exact:1 + +[43/161] 043 - gray_black.jpg + GT: [gray, black] + VLM: [black, grey] (5 jersey(s), 39.4s) + PASS exact:1, similar:1 + +[44/161] 044 - purple_black.jpg + GT: [purple, black] + VLM: [purple] (8 jersey(s), 35.7s) + PARTIAL exact:1, MISS:black + +[45/161] 045 - purple.jpg + GT: [purple] + VLM: [purple] (3 jersey(s), 34.7s) + PASS exact:1 + +[46/161] 046 - green.jpg + GT: [green] + VLM: [black] (8 jersey(s), 39.6s) + FAIL MISS:green, extra:black + +[47/161] 047 - purple_white.jpg + GT: [purple] + VLM: [purple] (3 jersey(s), 6.5s) + PASS exact:1 + +[48/161] 048 - red.jpg + GT: [red] + VLM: [(none)] (0 jersey(s), 7.4s) + FAIL MISS:red + +[49/161] 049 - white_gold.jpg + GT: [gold] + VLM: [yellow] (2 jersey(s), 3.3s) + PASS similar:1 + +[50/161] 050 - white_orange.jpg + GT: [orange] + VLM: [orange] (6 jersey(s), 39.2s) + PASS exact:1 + +[51/161] 051 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 3.1s) + PASS exact:1 + +[52/161] 052 - black_gold.jpg + GT: [black, gold] + VLM: [black] (1 jersey(s), 3.2s) + PARTIAL exact:1, MISS:gold + +[53/161] 053 - black_white.jpg + GT: [black] + VLM: [(none)] (1 jersey(s), 3.2s) + FAIL MISS:black + +[54/161] 054 - white_blue.jpg + GT: [blue] + VLM: [blue] (2 jersey(s), 3.5s) + PASS exact:1 + +[55/161] 055 - green_gold.jpg + GT: [green, gold] + VLM: [green, yellow] (2 jersey(s), 5.8s) + PASS exact:1, similar:1 + +[56/161] 056 - white_red.jpg + GT: [red] + VLM: [red] (4 jersey(s), 12.5s) + PASS exact:1 + +[57/161] 057 - white_gold or yellow.jpg + GT: [gold|yellow] + VLM: [(none)] (1 jersey(s), 4.1s) + FAIL MISS:gold|yellow + +[58/161] 058 - purple.jpg + GT: [purple] + VLM: [purple] (4 jersey(s), 5.3s) + PASS exact:1 + +[59/161] 059 - black_gold.jpg + GT: [black, gold] + VLM: [gold] (1 jersey(s), 3.4s) + PARTIAL exact:1, MISS:black + +[60/161] 060 - gray_navy blue.jpg + GT: [gray, navy blue] + VLM: [blue] (2 jersey(s), 5.7s) + PARTIAL similar:1, MISS:gray + +[61/161] 061 - brown or orange.jpg + GT: [brown|orange] + VLM: [orange] (1 jersey(s), 3.0s) + PASS exact:1 + +[62/161] 062 - orange_blue.jpg + GT: [orange, blue] + VLM: [blue, orange] (2 jersey(s), 5.7s) + PASS exact:2 + +[63/161] 063 - dark brown.jpg + GT: [dark brown] + VLM: [brown] (1 jersey(s), 5.1s) + PASS similar:1 + +[64/161] 064 - green_white.jpg + GT: [green] + VLM: [green] (1 jersey(s), 4.0s) + PASS exact:1 + +[65/161] 065 - green_gold.jpg + GT: [green, gold] + VLM: [green, yellow] (4 jersey(s), 38.3s) + PASS exact:1, similar:1 + +[66/161] 066 - yellow.jpg + GT: [yellow] + VLM: [yellow] (1 jersey(s), 3.3s) + PASS exact:1 + +[67/161] 067 - red_white.jpg + GT: [red] + VLM: [red] (5 jersey(s), 10.7s) + PASS exact:1 + +[68/161] 068 - gold.jpg + GT: [gold] + VLM: [gold] (1 jersey(s), 6.1s) + PASS exact:1 + +[69/161] 069 - red_white.jpg + GT: [red] + VLM: [(none)] (5 jersey(s), 39.4s) + FAIL MISS:red + +[70/161] 070 - green_white.jpg + GT: [green] + VLM: [green] (3 jersey(s), 6.2s) + PASS exact:1 + +[71/161] 071 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 11.6s) + PASS exact:1 + +[72/161] 072 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 4.7s) + PASS exact:1 + +[73/161] 073 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (1 jersey(s), 4.8s) + PASS exact:1 + +[74/161] 074 - white_orange.jpg + GT: [orange] + VLM: [(none)] (1 jersey(s), 7.0s) + FAIL MISS:orange + +[75/161] 075 - green_white.jpg + GT: [green] + VLM: [green] (1 jersey(s), 3.4s) + PASS exact:1 + +[76/161] 076 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (4 jersey(s), 8.5s) + PASS exact:1 + +[77/161] 077 - teal_white.jpg + GT: [teal] + VLM: [green] (5 jersey(s), 37.9s) + FAIL MISS:teal, extra:green + +[78/161] 078 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 6.8s) + PASS exact:1 + +[79/161] 079 - blue_maroon.jpg + GT: [blue, maroon] + VLM: [blue, maroon] (6 jersey(s), 7.7s) + PASS exact:2 + +[80/161] 080 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (1 jersey(s), 4.4s) + PASS similar:1 + +[81/161] 081 - navy blue.jpg + GT: [navy blue] + VLM: [blue] (2 jersey(s), 4.4s) + PASS similar:1 + +[82/161] 082 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (3 jersey(s), 6.8s) + PASS similar:1 + +[83/161] 083 - dark brown_white.jpg + GT: [dark brown] + VLM: [black] (2 jersey(s), 10.1s) + FAIL MISS:dark brown, extra:black + +[84/161] 084 - dark brown_yellow.jpg + GT: [dark brown, yellow] + VLM: [brown, yellow] (2 jersey(s), 3.4s) + PASS exact:1, similar:1 + +[85/161] 085 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 9.2s) + PASS exact:1 + +[86/161] 086 - dark brown_white.jpg + GT: [dark brown] + VLM: [brown] (1 jersey(s), 5.7s) + PASS similar:1 + +[87/161] 087 - white_light blue.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 8.4s) + PASS exact:1 + +[88/161] 088 - white_maroon.jpg + GT: [maroon] + VLM: [(none)] (2 jersey(s), 5.3s) + FAIL MISS:maroon + +[89/161] 089 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 7.4s) + PASS exact:1 + +[90/161] 090 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (5 jersey(s), 36.7s) + PASS exact:1 + +[91/161] 091 - teal.jpg + GT: [teal] + VLM: [teal] (3 jersey(s), 6.0s) + PASS exact:1 + +[92/161] 092 - green_white.jpg + GT: [green] + VLM: [green] (6 jersey(s), 10.9s) + PASS exact:1 + +[93/161] 093 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (2 jersey(s), 4.5s) + PASS similar:1 + +[94/161] 094 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 6.6s) + PASS exact:1 + +[95/161] 095 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 36.8s) + PASS exact:1 + +[96/161] 096 - orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 2.7s) + PASS exact:1 + +[97/161] 097 - gray_black.jpg + GT: [gray, black] + VLM: [grey] (3 jersey(s), 36.8s) + PARTIAL similar:1, MISS:black + +[98/161] 098 - teal_white.jpg + GT: [teal] + VLM: [teal] (2 jersey(s), 6.7s) + PASS exact:1 + +[99/161] 099 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 8.1s) + PASS exact:1 + +[100/161] 100 - orange_white.jpg + GT: [orange] + VLM: [orange] (4 jersey(s), 5.7s) + PASS exact:1 + +[101/161] 101 - green_white.jpg + GT: [green] + VLM: [green] (7 jersey(s), 12.1s) + PASS exact:1 + +[102/161] 102 - yellow-black.jpg + GT: [yellow, black] + VLM: [black] (1 jersey(s), 3.4s) + PARTIAL exact:1, MISS:yellow + +[103/161] 103 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 18.0s) + PASS exact:1 + +[104/161] 104 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 35.2s) + PASS exact:1 + +[105/161] 105 - orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 5.3s) + PASS exact:1 + +[106/161] 106 - black_gray.jpg + GT: [black, gray] + VLM: [black, grey] (2 jersey(s), 34.5s) + PASS exact:1, similar:1 + +[107/161] 107 - orange_white.jpg + GT: [orange] + VLM: [orange] (3 jersey(s), 4.7s) + PASS exact:1 + +[108/161] 108 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 4.5s) + PASS exact:1 + +[109/161] 109 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 4.7s) + PASS exact:1 + +[110/161] 110 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 9.0s) + PASS exact:1 + +[111/161] 111 - orange_white.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 37.6s) + PASS exact:1 + +[112/161] 112 - orange_white.jpg + GT: [orange] + VLM: [(none)] (0 jersey(s), 6.8s) + FAIL MISS:orange + +[113/161] 113 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 3.4s) + PASS exact:1 + +[114/161] 114 - black_white.jpg + GT: [black] + VLM: [black] (2 jersey(s), 5.1s) + PASS exact:1 + +[115/161] 115 - navy blue_maroon.jpg + GT: [navy blue, maroon] + VLM: [blue, red] (4 jersey(s), 7.7s) + PARTIAL similar:1, MISS:maroon, extra:red + +[116/161] 116 - gray_white.jpg + GT: [gray] + VLM: [grey] (2 jersey(s), 7.1s) + PASS similar:1 + +[117/161] 117 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 3.8s) + PASS exact:1 + +[118/161] 118 - dark blue_white.jpg + GT: [dark blue] + VLM: [navy blue] (2 jersey(s), 7.9s) + PASS similar:1 + +[119/161] 119 - black_yellow.jpg + GT: [black, yellow] + VLM: [black, yellow] (4 jersey(s), 8.5s) + PASS exact:2 + +[120/161] 120 - red_dark blue.jpg + GT: [red, dark blue] + VLM: [blue, red] (3 jersey(s), 20.5s) + PASS exact:1, similar:1 + +[121/161] 121 - orange_white.jpg + GT: [orange] + VLM: [orange] (3 jersey(s), 6.5s) + PASS exact:1 + +[122/161] 122 - gray.jpg + GT: [gray] + VLM: [grey] (1 jersey(s), 3.4s) + PASS similar:1 + +[123/161] 123 - teal_white.jpg + GT: [teal] + VLM: [teal] (4 jersey(s), 20.7s) + PASS exact:1 + +[124/161] 124 - dark blue_white.jpg + GT: [dark blue] + VLM: [navy blue] (4 jersey(s), 7.8s) + PASS similar:1 + +[125/161] 125 - dark blue_maroon.jpg + GT: [dark blue, maroon] + VLM: [navy, red] (3 jersey(s), 7.7s) + PARTIAL similar:1, MISS:maroon, extra:red + +[126/161] 126 - white_blue.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 7.5s) + PASS exact:1 + +[127/161] 127 - yellow.jpg + GT: [yellow] + VLM: [black, yellow] (5 jersey(s), 22.9s) + PARTIAL exact:1, extra:black + +[128/161] 128 - green_white.jpg + GT: [green] + VLM: [green] (1 jersey(s), 36.1s) + PASS exact:1 + +[129/161] 129 - blue_white.jpg + GT: [blue] + VLM: [(none)] (3 jersey(s), 6.0s) + FAIL MISS:blue + +[130/161] 130 - yellow_black.jpg + GT: [yellow, black] + VLM: [yellow] (1 jersey(s), 3.3s) + PARTIAL exact:1, MISS:black + +[131/161] 131 - purple_orange.jpg + GT: [purple, orange] + VLM: [orange, purple] (3 jersey(s), 5.4s) + PASS exact:2 + +[132/161] 132 - brown_white.jpg + GT: [brown] + VLM: [orange] (3 jersey(s), 30.8s) + FAIL MISS:brown, extra:orange + +[133/161] 133 - light blue.png + GT: [light blue] + VLM: [light blue] (7 jersey(s), 42.4s) + PASS exact:1 + +[134/161] 134 - teal_white.jpg + GT: [teal] + VLM: [blue] (1 jersey(s), 7.1s) + FAIL MISS:teal, extra:blue + +[135/161] 135 - green.jpg + GT: [green] + VLM: [green] (1 jersey(s), 3.6s) + PASS exact:1 + +[136/161] 136 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 3.5s) + PASS exact:1 + +[137/161] 137 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 7.3s) + PASS exact:1 + +[138/161] 138 - maroon.jpg + GT: [maroon] + VLM: [red] (1 jersey(s), 3.5s) + FAIL MISS:maroon, extra:red + +[139/161] 139 - dark blue_white.jpg + GT: [dark blue] + VLM: [navy blue] (1 jersey(s), 12.2s) + PASS similar:1 + +[140/161] 140 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 4.0s) + PASS exact:1 + +[141/161] 141 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (3 jersey(s), 4.7s) + PASS exact:1 + +[142/161] 142 - orange_white.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 4.0s) + PASS exact:1 + +[143/161] 143 - blue_white.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 5.9s) + PASS exact:1 + +[144/161] 144 - green.jpg + GT: [green] + VLM: [green] (13 jersey(s), 8.2s) + PASS exact:1 + +[145/161] 145 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 8.0s) + PASS exact:1 + +[146/161] 146 - red_gray.jpg + GT: [red, gray] + VLM: [grey, red] (2 jersey(s), 4.2s) + PASS exact:1, similar:1 + +[147/161] 147 - green.jpg + GT: [green] + VLM: [green] (3 jersey(s), 4.8s) + PASS exact:1 + +[148/161] 148 - yellow_purple.jpg + GT: [yellow, purple] + VLM: [purple, yellow] (2 jersey(s), 6.0s) + PASS exact:2 + +[149/161] 149 - blue_white.jpg + GT: [blue] + VLM: [blue] (4 jersey(s), 37.0s) + PASS exact:1 + +[150/161] 150 - green_gray.jpg + GT: [green, gray] + VLM: [black] (2 jersey(s), 12.3s) + FAIL MISS:green,gray, extra:black + +[151/161] 151 - yellow_black.jpg + GT: [yellow, black] + VLM: [navy, yellow] (6 jersey(s), 39.2s) + PARTIAL exact:1, MISS:black, extra:navy + +[152/161] 152 - pink_dark blue.jpg + GT: [pink, dark blue] + VLM: [navy blue, pink] (3 jersey(s), 5.9s) + PASS exact:1, similar:1 + +[153/161] 153 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 5.2s) + PASS exact:1 + +[154/161] 154 - dark brown.jpeg + GT: [dark brown] + VLM: [brown] (5 jersey(s), 7.0s) + PASS similar:1 + +[155/161] 155 - white_green_gray_purple_yellow.jpg + GT: [green, gray, purple, yellow] + VLM: [grey, purple, yellow] (5 jersey(s), 7.7s) + PARTIAL exact:2, similar:1, MISS:green + +[156/161] 156 - maroon_gray.jpg + GT: [maroon, gray] + VLM: [maroon] (3 jersey(s), 35.1s) + PARTIAL exact:1, MISS:gray + +[157/161] 157 - blue_white.jpg + GT: [blue] + VLM: [blue] (4 jersey(s), 40.2s) + PASS exact:1 + +[158/161] 158 - dark blue_yellow.jpg + GT: [dark blue, yellow] + VLM: [dark blue, yellow] (6 jersey(s), 33.8s) + PASS exact:2 + +[159/161] 159 - blue_white.jpg + GT: [blue] + VLM: [blue] (5 jersey(s), 36.7s) + PASS exact:1 + +[160/161] 160 - blue_white.jpg + GT: [blue] + VLM: [(none)] (1 jersey(s), 4.1s) + FAIL MISS:blue + +[161/161] 161 - light blue_white.jpg + GT: [light blue] + VLM: [blue] (2 jersey(s), 4.8s) + FAIL MISS:light blue, extra:blue + +================================================================================ +ACCURACY SUMMARY (gemini-3-flash-preview) +================================================================================ +Images processed: 161 +Errors: 0 +Total time: 253.2s (1.6s avg) + +Ground truth colors: 202 (excluding white) +VLM unique colors: 175 (excluding white) + +--- Recall (did VLM find each ground truth color?) --- + Exact match: 126 / 202 (62.4%) + Similar match: 35 / 202 (17.3%) + Total found: 161 / 202 (79.7%) + Missed: 41 / 202 (20.3%) + +--- Precision (are VLM colors correct?) --- + Exact match: 126 / 175 (72.0%) + Similar match: 34 / 175 (19.4%) + Total correct: 160 / 175 (91.4%) + Extra/wrong: 15 / 175 (8.6%) + +--- Similar-Match Confusions (expected -> got) --- + gray -> grey x10 + navy blue -> blue x6 + dark brown -> brown x5 + dark blue -> navy blue x5 + gold -> yellow x3 + dark blue -> blue x3 + navy blue -> dark blue x1 + navy -> navy blue x1 + dark blue -> navy x1 + +--- Most Missed Ground Truth Colors --- + black 7 ####### + gray 6 ###### + maroon 6 ###### + light blue 3 ### + red 3 ### + blue 3 ### + green 3 ### + gold 2 ## + orange 2 ## + teal 2 ## + gold|yellow 1 # + dark brown 1 # + yellow 1 # + brown 1 # + +--- Most Common Extra/Wrong VLM Colors --- + blue 4 #### + red 4 #### + black 4 #### + green 1 # + orange 1 # + navy 1 # + +--- Per-Image Verdict --- + PASS 120 + PARTIAL 20 + FAIL 21 + +--- Failed Images (21) --- + 013 - light blue.jpg + missed: light blue + extra: blue + 016 - maroon.jpg + missed: maroon + 029 -maroon_white.jpg + missed: maroon + extra: red + 034 - light blue.jpg + missed: light blue + extra: blue + 046 - green.jpg + missed: green + extra: black + 048 - red.jpg + missed: red + 053 - black_white.jpg + missed: black + 057 - white_gold or yellow.jpg + missed: gold|yellow + 069 - red_white.jpg + missed: red + 074 - white_orange.jpg + missed: orange + 077 - teal_white.jpg + missed: teal + extra: green + 083 - dark brown_white.jpg + missed: dark brown + extra: black + 088 - white_maroon.jpg + missed: maroon + 112 - orange_white.jpg + missed: orange + 129 - blue_white.jpg + missed: blue + 132 - brown_white.jpg + missed: brown + extra: orange + 134 - teal_white.jpg + missed: teal + extra: blue + 138 - maroon.jpg + missed: maroon + extra: red + 150 - green_gray.jpg + missed: green, gray + extra: black + 160 - blue_white.jpg + missed: blue + 161 - light blue_white.jpg + missed: light blue + extra: blue + +======================================== +Qwen3-VL-8B + jersey_prompt_capstone.txt +Started: Tue Mar 3 05:10:58 PM MST 2026 +======================================== +Images to process: 161 +Server: http://agx:8080 +Prompt: /home/rmcewen/data/dev.python/jersey_test/jersey_prompt_capstone.txt (1511 chars) +================================================================================ + +[1/161] 001 -brown_white or dark brown.jpg + GT: [brown, dark brown] + VLM: [black] (2 jersey(s), 8.2s) + FAIL MISS:brown,dark brown, extra:black + +[2/161] 002 - yellow.jpg + GT: [yellow] + VLM: [yellow] (2 jersey(s), 6.0s) + PASS exact:1 + +[3/161] 003 - dark blue.jpg + GT: [dark blue] + VLM: [blue] (3 jersey(s), 8.3s) + PASS similar:1 + +[4/161] 004 - purple_light blue.jpg + GT: [purple, light blue] + VLM: [light blue, purple] (3 jersey(s), 11.9s) + PASS exact:2 + +[5/161] 005 - white or gray_purple.jpg + GT: [gray, purple] + VLM: [purple] (1 jersey(s), 3.8s) + PARTIAL exact:1, MISS:gray + +[6/161] 006 - navy blue.jpg + GT: [navy blue] + VLM: [blue] (1 jersey(s), 4.2s) + PASS similar:1 + +[7/161] 007 - brown_white.jpg + GT: [brown] + VLM: [brown] (2 jersey(s), 6.0s) + PASS exact:1 + +[8/161] 008 -red or orange.jpg + GT: [red|orange] + VLM: [red] (1 jersey(s), 3.2s) + PASS exact:1 + +[9/161] 009 - white_red.jpg + GT: [red] + VLM: [gold, red] (3 jersey(s), 10.8s) + PARTIAL exact:1, extra:gold + +[10/161] 010 - white_black.jpg + GT: [black] + VLM: [black] (3 jersey(s), 10.9s) + PASS exact:1 + +[11/161] 011 - white or gray_purple.jpg + GT: [gray, purple] + VLM: [purple] (4 jersey(s), 13.8s) + PARTIAL exact:1, MISS:gray + +[12/161] 012 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 7.3s) + PASS exact:1 + +[13/161] 013 - light blue.jpg + GT: [light blue] + VLM: [blue] (2 jersey(s), 7.5s) + FAIL MISS:light blue, extra:blue + +[14/161] 014 - orange_dark blue or purple.jpg + GT: [orange, dark blue|purple] + VLM: [orange, purple] (3 jersey(s), 11.0s) + PASS exact:2 + +[15/161] 015 - green.jpg + GT: [green] + VLM: [green] (2 jersey(s), 5.4s) + PASS exact:1 + +[16/161] 016 - maroon.jpg + GT: [maroon] + VLM: [(none)] (0 jersey(s), 1.7s) + FAIL MISS:maroon + +[17/161] 017 - brown_white.jpg + GT: [brown] + VLM: [black] (2 jersey(s), 6.9s) + FAIL MISS:brown, extra:black + +[18/161] 018 - gray_red.jpg + GT: [gray, red] + VLM: [gray, red] (2 jersey(s), 7.3s) + PASS exact:2 + +[19/161] 019 - maroon_gold.jpg + GT: [maroon, gold] + VLM: [red] (1 jersey(s), 3.7s) + FAIL MISS:maroon,gold, extra:red + +[20/161] 020 - white_brown or orange.jpg + GT: [brown|orange] + VLM: [orange] (2 jersey(s), 6.2s) + PASS exact:1 + +[21/161] 021 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 6.1s) + PASS exact:1 + +[22/161] 022 - black_light blue.jpg + GT: [black, light blue] + VLM: [light blue] (1 jersey(s), 3.8s) + PARTIAL exact:1, MISS:black + +[23/161] 023 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 5.9s) + PASS exact:1 + +[24/161] 024 - white_pink.jpg + GT: [pink] + VLM: [pink] (2 jersey(s), 7.7s) + PASS exact:1 + +[25/161] 025 - blue_green.jpg + GT: [blue, green] + VLM: [green] (1 jersey(s), 3.2s) + PARTIAL exact:1, MISS:blue + +[26/161] 026 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.9s) + PASS exact:1 + +[27/161] 027 - red_white.jpg + GT: [red] + VLM: [red] (5 jersey(s), 16.1s) + PASS exact:1 + +[28/161] 028 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.9s) + PASS exact:1 + +[29/161] 029 -maroon_white.jpg + GT: [maroon] + VLM: [red] (2 jersey(s), 7.8s) + FAIL MISS:maroon, extra:red + +[30/161] 030 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (2 jersey(s), 5.9s) + PASS similar:1 + +[31/161] 031 - brown_white.jpg + GT: [brown] + VLM: [brown] (2 jersey(s), 6.0s) + PASS exact:1 + +[32/161] 032 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 6.1s) + PASS exact:1 + +[33/161] 033 - navy blue_white or gray.jpg + GT: [navy blue, gray] + VLM: [blue] (3 jersey(s), 10.9s) + PARTIAL similar:1, MISS:gray + +[34/161] 034 - light blue.jpg + GT: [light blue] + VLM: [blue] (1 jersey(s), 3.7s) + FAIL MISS:light blue, extra:blue + +[35/161] 035 -green_gold or yellow.jpg + GT: [green, gold|yellow] + VLM: [green, yellow] (2 jersey(s), 8.0s) + PASS exact:2 + +[36/161] 036 - light blue_white.jpg + GT: [light blue] + VLM: [blue] (4 jersey(s), 13.8s) + FAIL MISS:light blue, extra:blue + +[37/161] 037 -navy_white.jpg + GT: [navy] + VLM: [blue] (3 jersey(s), 10.1s) + PASS similar:1 + +[38/161] 038 - red_white.jpg + GT: [red] + VLM: [red] (3 jersey(s), 11.0s) + PASS exact:1 + +[39/161] 039 - gray_white.jpg + GT: [gray] + VLM: [gray] (2 jersey(s), 7.9s) + PASS exact:1 + +[40/161] 040 - maroon_gray.jpg + GT: [maroon, gray] + VLM: [maroon] (1 jersey(s), 5.1s) + PARTIAL exact:1, MISS:gray + +[41/161] 041 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (9 jersey(s), 28.9s) + PASS similar:1 + +[42/161] 042 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 3.8s) + PASS exact:1 + +[43/161] 043 - gray_black.jpg + GT: [gray, black] + VLM: [black, gray] (2 jersey(s), 8.0s) + PASS exact:2 + +[44/161] 044 - purple_black.jpg + GT: [purple, black] + VLM: [purple] (7 jersey(s), 22.5s) + PARTIAL exact:1, MISS:black + +[45/161] 045 - purple.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 7.9s) + PASS exact:1 + +[46/161] 046 - green.jpg + GT: [green] + VLM: [black] (15 jersey(s), 46.5s) + FAIL MISS:green, extra:black + +[47/161] 047 - purple_white.jpg + GT: [purple] + VLM: [purple] (3 jersey(s), 10.7s) + PASS exact:1 + +[48/161] 048 - red.jpg + GT: [red] + VLM: [red] (1 jersey(s), 4.9s) + PASS exact:1 + +[49/161] 049 - white_gold.jpg + GT: [gold] + VLM: [yellow] (2 jersey(s), 6.1s) + PASS similar:1 + +[50/161] 050 - white_orange.jpg + GT: [orange] + VLM: [orange] (4 jersey(s), 13.8s) + PASS exact:1 + +[51/161] 051 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 3.8s) + PASS exact:1 + +[52/161] 052 - black_gold.jpg + GT: [black, gold] + VLM: [black] (1 jersey(s), 4.8s) + PARTIAL exact:1, MISS:gold + +[53/161] 053 - black_white.jpg + GT: [black] + VLM: [(none)] (1 jersey(s), 3.7s) + FAIL MISS:black + +[54/161] 054 - white_blue.jpg + GT: [blue] + VLM: [blue] (2 jersey(s), 5.9s) + PASS exact:1 + +[55/161] 055 - green_gold.jpg + GT: [green, gold] + VLM: [green, yellow] (2 jersey(s), 7.7s) + PASS exact:1, similar:1 + +[56/161] 056 - white_red.jpg + GT: [red] + VLM: [red] (2 jersey(s), 5.9s) + PASS exact:1 + +[57/161] 057 - white_gold or yellow.jpg + GT: [gold|yellow] + VLM: [(none)] (1 jersey(s), 3.7s) + FAIL MISS:gold|yellow + +[58/161] 058 - purple.jpg + GT: [purple] + VLM: [purple] (4 jersey(s), 14.0s) + PASS exact:1 + +[59/161] 059 - black_gold.jpg + GT: [black, gold] + VLM: [gold] (1 jersey(s), 3.8s) + PARTIAL exact:1, MISS:black + +[60/161] 060 - gray_navy blue.jpg + GT: [gray, navy blue] + VLM: [blue] (2 jersey(s), 6.0s) + PARTIAL similar:1, MISS:gray + +[61/161] 061 - brown or orange.jpg + GT: [brown|orange] + VLM: [orange] (1 jersey(s), 3.7s) + PASS exact:1 + +[62/161] 062 - orange_blue.jpg + GT: [orange, blue] + VLM: [blue, orange] (2 jersey(s), 5.6s) + PASS exact:2 + +[63/161] 063 - dark brown.jpg + GT: [dark brown] + VLM: [black] (1 jersey(s), 3.7s) + FAIL MISS:dark brown, extra:black + +[64/161] 064 - green_white.jpg + GT: [green] + VLM: [green] (1 jersey(s), 4.8s) + PASS exact:1 + +[65/161] 065 - green_gold.jpg + GT: [green, gold] + VLM: [green, yellow] (3 jersey(s), 10.4s) + PASS exact:1, similar:1 + +[66/161] 066 - yellow.jpg + GT: [yellow] + VLM: [yellow] (1 jersey(s), 3.5s) + PASS exact:1 + +[67/161] 067 - red_white.jpg + GT: [red] + VLM: [red] (4 jersey(s), 13.8s) + PASS exact:1 + +[68/161] 068 - gold.jpg + GT: [gold] + VLM: [gold] (1 jersey(s), 3.7s) + PASS exact:1 + +[69/161] 069 - red_white.jpg + GT: [red] + VLM: [red] (5 jersey(s), 16.6s) + PASS exact:1 + +[70/161] 070 - green_white.jpg + GT: [green] + VLM: [green] (3 jersey(s), 8.3s) + PASS exact:1 + +[71/161] 071 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 7.9s) + PASS exact:1 + +[72/161] 072 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 7.5s) + PASS exact:1 + +[73/161] 073 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (1 jersey(s), 3.4s) + PASS exact:1 + +[74/161] 074 - white_orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 7.4s) + PASS exact:1 + +[75/161] 075 - green_white.jpg + GT: [green] + VLM: [green] (1 jersey(s), 4.8s) + PASS exact:1 + +[76/161] 076 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (4 jersey(s), 14.2s) + PASS exact:1 + +[77/161] 077 - teal_white.jpg + GT: [teal] + VLM: [green] (3 jersey(s), 10.4s) + FAIL MISS:teal, extra:green + +[78/161] 078 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 5.9s) + PASS exact:1 + +[79/161] 079 - blue_maroon.jpg + GT: [blue, maroon] + VLM: [blue, red] (4 jersey(s), 13.8s) + PARTIAL exact:1, MISS:maroon, extra:red + +[80/161] 080 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (1 jersey(s), 3.5s) + PASS similar:1 + +[81/161] 081 - navy blue.jpg + GT: [navy blue] + VLM: [blue] (2 jersey(s), 5.8s) + PASS similar:1 + +[82/161] 082 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (3 jersey(s), 10.6s) + PASS similar:1 + +[83/161] 083 - dark brown_white.jpg + GT: [dark brown] + VLM: [black] (1 jersey(s), 3.7s) + FAIL MISS:dark brown, extra:black + +[84/161] 084 - dark brown_yellow.jpg + GT: [dark brown, yellow] + VLM: [black, yellow] (2 jersey(s), 6.0s) + PARTIAL exact:1, MISS:dark brown, extra:black + +[85/161] 085 - green_white.jpg + GT: [green] + VLM: [green] (1 jersey(s), 3.6s) + PASS exact:1 + +[86/161] 086 - dark brown_white.jpg + GT: [dark brown] + VLM: [brown] (1 jersey(s), 5.0s) + PASS similar:1 + +[87/161] 087 - white_light blue.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 6.0s) + PASS exact:1 + +[88/161] 088 - white_maroon.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 7.9s) + PASS exact:1 + +[89/161] 089 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 11.0s) + PASS exact:1 + +[90/161] 090 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (4 jersey(s), 14.2s) + PASS exact:1 + +[91/161] 091 - teal.jpg + GT: [teal] + VLM: [teal] (2 jersey(s), 8.1s) + PASS exact:1 + +[92/161] 092 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 13.8s) + PASS exact:1 + +[93/161] 093 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (2 jersey(s), 5.9s) + PASS similar:1 + +[94/161] 094 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 12.5s) + PASS exact:1 + +[95/161] 095 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.9s) + PASS exact:1 + +[96/161] 096 - orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 6.7s) + PASS exact:1 + +[97/161] 097 - gray_black.jpg + GT: [gray, black] + VLM: [gray] (2 jersey(s), 8.0s) + PARTIAL exact:1, MISS:black + +[98/161] 098 - teal_white.jpg + GT: [teal] + VLM: [teal] (2 jersey(s), 6.9s) + PASS exact:1 + +[99/161] 099 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 12.2s) + PASS exact:1 + +[100/161] 100 - orange_white.jpg + GT: [orange] + VLM: [orange] (4 jersey(s), 13.8s) + PASS exact:1 + +[101/161] 101 - green_white.jpg + GT: [green] + VLM: [green] (5 jersey(s), 17.0s) + PASS exact:1 + +[102/161] 102 - yellow-black.jpg + GT: [yellow, black] + VLM: [black, yellow] (2 jersey(s), 8.0s) + PASS exact:2 + +[103/161] 103 - green_white.jpg + GT: [green] + VLM: [green] (5 jersey(s), 17.3s) + PASS exact:1 + +[104/161] 104 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 11.0s) + PASS exact:1 + +[105/161] 105 - orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 7.4s) + PASS exact:1 + +[106/161] 106 - black_gray.jpg + GT: [black, gray] + VLM: [black, gray] (2 jersey(s), 7.3s) + PASS exact:2 + +[107/161] 107 - orange_white.jpg + GT: [orange] + VLM: [orange] (3 jersey(s), 10.7s) + PASS exact:1 + +[108/161] 108 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 7.9s) + PASS exact:1 + +[109/161] 109 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 6.0s) + PASS exact:1 + +[110/161] 110 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 13.9s) + PASS exact:1 + +[111/161] 111 - orange_white.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 6.1s) + PASS exact:1 + +[112/161] 112 - orange_white.jpg + GT: [orange] + VLM: [(none)] (1 jersey(s), 3.6s) + FAIL MISS:orange + +[113/161] 113 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 3.8s) + PASS exact:1 + +[114/161] 114 - black_white.jpg + GT: [black] + VLM: [black] (2 jersey(s), 6.3s) + PASS exact:1 + +[115/161] 115 - navy blue_maroon.jpg + GT: [navy blue, maroon] + VLM: [blue, red] (4 jersey(s), 13.8s) + PARTIAL similar:1, MISS:maroon, extra:red + +[116/161] 116 - gray_white.jpg + GT: [gray] + VLM: [gray] (2 jersey(s), 6.0s) + PASS exact:1 + +[117/161] 117 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 6.2s) + PASS exact:1 + +[118/161] 118 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (2 jersey(s), 7.4s) + PASS similar:1 + +[119/161] 119 - black_yellow.jpg + GT: [black, yellow] + VLM: [black, yellow] (3 jersey(s), 10.9s) + PASS exact:2 + +[120/161] 120 - red_dark blue.jpg + GT: [red, dark blue] + VLM: [blue, red] (3 jersey(s), 10.6s) + PASS exact:1, similar:1 + +[121/161] 121 - orange_white.jpg + GT: [orange] + VLM: [orange] (3 jersey(s), 11.0s) + PASS exact:1 + +[122/161] 122 - gray.jpg + GT: [gray] + VLM: [gray] (1 jersey(s), 5.1s) + PASS exact:1 + +[123/161] 123 - teal_white.jpg + GT: [teal] + VLM: [teal] (4 jersey(s), 13.9s) + PASS exact:1 + +[124/161] 124 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (4 jersey(s), 13.7s) + PASS similar:1 + +[125/161] 125 - dark blue_maroon.jpg + GT: [dark blue, maroon] + VLM: [blue, red] (2 jersey(s), 8.2s) + PARTIAL similar:1, MISS:maroon, extra:red + +[126/161] 126 - white_blue.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 10.8s) + PASS exact:1 + +[127/161] 127 - yellow.jpg + GT: [yellow] + VLM: [yellow] (4 jersey(s), 13.9s) + PASS exact:1 + +[128/161] 128 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.9s) + PASS exact:1 + +[129/161] 129 - blue_white.jpg + GT: [blue] + VLM: [blue] (4 jersey(s), 13.8s) + PASS exact:1 + +[130/161] 130 - yellow_black.jpg + GT: [yellow, black] + VLM: [black, yellow] (2 jersey(s), 8.4s) + PASS exact:2 + +[131/161] 131 - purple_orange.jpg + GT: [purple, orange] + VLM: [orange, purple] (3 jersey(s), 8.3s) + PASS exact:2 + +[132/161] 132 - brown_white.jpg + GT: [brown] + VLM: [orange] (3 jersey(s), 10.8s) + FAIL MISS:brown, extra:orange + +[133/161] 133 - light blue.png + GT: [light blue] + VLM: [light blue] (7 jersey(s), 23.5s) + PASS exact:1 + +[134/161] 134 - teal_white.jpg + GT: [teal] + VLM: [blue] (1 jersey(s), 5.0s) + FAIL MISS:teal, extra:blue + +[135/161] 135 - green.jpg + GT: [green] + VLM: [green] (1 jersey(s), 3.9s) + PASS exact:1 + +[136/161] 136 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 6.2s) + PASS exact:1 + +[137/161] 137 - green_white.jpg + GT: [green] + VLM: [green] (3 jersey(s), 10.9s) + PASS exact:1 + +[138/161] 138 - maroon.jpg + GT: [maroon] + VLM: [red] (1 jersey(s), 3.8s) + FAIL MISS:maroon, extra:red + +[139/161] 139 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (2 jersey(s), 6.0s) + PASS similar:1 + +[140/161] 140 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 5.7s) + PASS exact:1 + +[141/161] 141 - light blue_white.jpg + GT: [light blue] + VLM: [blue] (3 jersey(s), 8.6s) + FAIL MISS:light blue, extra:blue + +[142/161] 142 - orange_white.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 6.1s) + PASS exact:1 + +[143/161] 143 - blue_white.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 11.0s) + PASS exact:1 + +[144/161] 144 - green.jpg + GT: [green] + VLM: [green] (12 jersey(s), 37.7s) + PASS exact:1 + +[145/161] 145 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.9s) + PASS exact:1 + +[146/161] 146 - red_gray.jpg + GT: [red, gray] + VLM: [gray, red] (2 jersey(s), 6.7s) + PASS exact:2 + +[147/161] 147 - green.jpg + GT: [green] + VLM: [green] (3 jersey(s), 8.3s) + PASS exact:1 + +[148/161] 148 - yellow_purple.jpg + GT: [yellow, purple] + VLM: [purple, yellow] (2 jersey(s), 7.9s) + PASS exact:2 + +[149/161] 149 - blue_white.jpg + GT: [blue] + VLM: [blue] (4 jersey(s), 13.7s) + PASS exact:1 + +[150/161] 150 - green_gray.jpg + GT: [green, gray] + VLM: [black] (2 jersey(s), 7.8s) + FAIL MISS:green,gray, extra:black + +[151/161] 151 - yellow_black.jpg + GT: [yellow, black] + VLM: [navy, yellow] (5 jersey(s), 17.1s) + PARTIAL exact:1, MISS:black, extra:navy + +[152/161] 152 - pink_dark blue.jpg + GT: [pink, dark blue] + VLM: [blue, pink] (2 jersey(s), 7.9s) + PASS exact:1, similar:1 + +[153/161] 153 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 8.1s) + PASS exact:1 + +[154/161] 154 - dark brown.jpeg + GT: [dark brown] + VLM: [brown] (5 jersey(s), 12.9s) + PASS similar:1 + +[155/161] 155 - white_green_gray_purple_yellow.jpg + GT: [green, gray, purple, yellow] + VLM: [purple, yellow] (4 jersey(s), 14.2s) + PARTIAL exact:2, MISS:green,gray + +[156/161] 156 - maroon_gray.jpg + GT: [maroon, gray] + VLM: [maroon] (2 jersey(s), 7.6s) + PARTIAL exact:1, MISS:gray + +[157/161] 157 - blue_white.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 8.3s) + PASS exact:1 + +[158/161] 158 - dark blue_yellow.jpg + GT: [dark blue, yellow] + VLM: [navy, yellow] (4 jersey(s), 14.0s) + PASS exact:1, similar:1 + +[159/161] 159 - blue_white.jpg + GT: [blue] + VLM: [blue] (4 jersey(s), 13.9s) + PASS exact:1 + +[160/161] 160 - blue_white.jpg + GT: [blue] + VLM: [(none)] (1 jersey(s), 3.8s) + FAIL MISS:blue + +[161/161] 161 - light blue_white.jpg + GT: [light blue] + VLM: [blue] (2 jersey(s), 5.8s) + FAIL MISS:light blue, extra:blue + +================================================================================ +ACCURACY SUMMARY +================================================================================ +Images processed: 161 +Errors: 0 +Total time: 1437.3s (8.9s avg) + +Ground truth colors: 202 (excluding white) +VLM unique colors: 181 (excluding white) + +--- Recall (did VLM find each ground truth color?) --- + Exact match: 134 / 202 (66.3%) + Similar match: 24 / 202 (11.9%) + Total found: 158 / 202 (78.2%) + Missed: 44 / 202 (21.8%) + +--- Precision (are VLM colors correct?) --- + Exact match: 134 / 181 (74.0%) + Similar match: 24 / 181 (13.3%) + Total correct: 158 / 181 (87.3%) + Extra/wrong: 23 / 181 (12.7%) + +--- Similar-Match Confusions (expected -> got) --- + dark blue -> blue x9 + navy blue -> blue x8 + gold -> yellow x3 + dark brown -> brown x2 + navy -> blue x1 + dark blue -> navy x1 + +--- Most Missed Ground Truth Colors --- + gray 8 ######## + maroon 7 ####### + black 6 ###### + light blue 5 ##### + dark brown 4 #### + brown 3 ### + green 3 ### + gold 2 ## + blue 2 ## + teal 2 ## + gold|yellow 1 # + orange 1 # + +--- Most Common Extra/Wrong VLM Colors --- + black 7 ####### + blue 6 ###### + red 6 ###### + gold 1 # + green 1 # + orange 1 # + navy 1 # + +--- Per-Image Verdict --- + PASS 120 + PARTIAL 19 + FAIL 22 + +--- Failed Images (22) --- + 001 -brown_white or dark brown.jpg + missed: brown, dark brown + extra: black + 013 - light blue.jpg + missed: light blue + extra: blue + 016 - maroon.jpg + missed: maroon + 017 - brown_white.jpg + missed: brown + extra: black + 019 - maroon_gold.jpg + missed: maroon, gold + extra: red + 029 -maroon_white.jpg + missed: maroon + extra: red + 034 - light blue.jpg + missed: light blue + extra: blue + 036 - light blue_white.jpg + missed: light blue + extra: blue + 046 - green.jpg + missed: green + extra: black + 053 - black_white.jpg + missed: black + 057 - white_gold or yellow.jpg + missed: gold|yellow + 063 - dark brown.jpg + missed: dark brown + extra: black + 077 - teal_white.jpg + missed: teal + extra: green + 083 - dark brown_white.jpg + missed: dark brown + extra: black + 112 - orange_white.jpg + missed: orange + 132 - brown_white.jpg + missed: brown + extra: orange + 134 - teal_white.jpg + missed: teal + extra: blue + 138 - maroon.jpg + missed: maroon + extra: red + 141 - light blue_white.jpg + missed: light blue + extra: blue + 150 - green_gray.jpg + missed: green, gray + extra: black + 160 - blue_white.jpg + missed: blue + 161 - light blue_white.jpg + missed: light blue + extra: blue + +======================================== +Gemini 3 Flash + jersey_prompt_capstone.txt +Started: Tue Mar 3 05:34:55 PM MST 2026 +======================================== +Model: gemini-3-flash-preview +Images to process: 161 +Concurrency: 8 workers +Prompt: /home/rmcewen/data/dev.python/jersey_test/jersey_prompt_capstone.txt (1511 chars) +================================================================================ +Pre-encoding images ... 161 images in 1.7s +Sending API requests ... + 1/161 API calls completed 2/161 API calls completed 3/161 API calls completed 4/161 API calls completed 5/161 API calls completed 6/161 API calls completed 7/161 API calls completed 8/161 API calls completed 9/161 API calls completed 10/161 API calls completed 11/161 API calls completed 12/161 API calls completed 13/161 API calls completed 14/161 API calls completed 15/161 API calls completed 16/161 API calls completed 17/161 API calls completed 18/161 API calls completed 19/161 API calls completed 20/161 API calls completed 21/161 API calls completed 22/161 API calls completed 23/161 API calls completed 24/161 API calls completed 25/161 API calls completed 26/161 API calls completed 27/161 API calls completed 28/161 API calls completed 29/161 API calls completed 30/161 API calls completed 31/161 API calls completed 32/161 API calls completed 33/161 API calls completed 34/161 API calls completed 35/161 API calls completed 36/161 API calls completed 37/161 API calls completed 38/161 API calls completed 39/161 API calls completed 40/161 API calls completed 41/161 API calls completed 42/161 API calls completed 43/161 API calls completed 44/161 API calls completed 45/161 API calls completed 46/161 API calls completed 47/161 API calls completed 48/161 API calls completed 49/161 API calls completed 50/161 API calls completed 51/161 API calls completed 52/161 API calls completed 53/161 API calls completed 54/161 API calls completed 55/161 API calls completed 56/161 API calls completed 57/161 API calls completed 58/161 API calls completed 59/161 API calls completed 60/161 API calls completed 61/161 API calls completed 62/161 API calls completed 63/161 API calls completed 64/161 API calls completed 65/161 API calls completed 66/161 API calls completed 67/161 API calls completed 68/161 API calls completed 69/161 API calls completed 70/161 API calls completed 71/161 API calls completed 72/161 API calls completed 73/161 API calls completed 74/161 API calls completed 75/161 API calls completed 76/161 API calls completed 77/161 API calls completed 78/161 API calls completed 79/161 API calls completed 80/161 API calls completed 81/161 API calls completed 82/161 API calls completed 83/161 API calls completed 84/161 API calls completed 85/161 API calls completed 86/161 API calls completed 87/161 API calls completed 88/161 API calls completed 89/161 API calls completed 90/161 API calls completed 91/161 API calls completed 92/161 API calls completed 93/161 API calls completed 94/161 API calls completed 95/161 API calls completed 96/161 API calls completed 97/161 API calls completed 98/161 API calls completed 99/161 API calls completed 100/161 API calls completed 101/161 API calls completed 102/161 API calls completed 103/161 API calls completed 104/161 API calls completed 105/161 API calls completed 106/161 API calls completed 107/161 API calls completed 108/161 API calls completed 109/161 API calls completed 110/161 API calls completed 111/161 API calls completed 112/161 API calls completed 113/161 API calls completed 114/161 API calls completed 115/161 API calls completed 116/161 API calls completed 117/161 API calls completed 118/161 API calls completed 119/161 API calls completed 120/161 API calls completed 121/161 API calls completed 122/161 API calls completed 123/161 API calls completed 124/161 API calls completed 125/161 API calls completed 126/161 API calls completed 127/161 API calls completed 128/161 API calls completed 129/161 API calls completed 130/161 API calls completed 131/161 API calls completed 132/161 API calls completed 133/161 API calls completed 134/161 API calls completed 135/161 API calls completed 136/161 API calls completed 137/161 API calls completed 138/161 API calls completed 139/161 API calls completed 140/161 API calls completed 141/161 API calls completed 142/161 API calls completed 143/161 API calls completed 144/161 API calls completed 145/161 API calls completed 146/161 API calls completed 147/161 API calls completed 148/161 API calls completed 149/161 API calls completed 150/161 API calls completed 151/161 API calls completed 152/161 API calls completed 153/161 API calls completed 154/161 API calls completed 155/161 API calls completed 156/161 API calls completed 157/161 API calls completed 158/161 API calls completed 159/161 API calls completed 160/161 API calls completed 161/161 API calls completed (259.8s total) +================================================================================ + +[1/161] 001 -brown_white or dark brown.jpg + GT: [brown, dark brown] + VLM: [brown] (1 jersey(s), 7.0s) + PASS exact:1, similar:1 + +[2/161] 002 - yellow.jpg + GT: [yellow] + VLM: [yellow] (2 jersey(s), 4.6s) + PASS exact:1 + +[3/161] 003 - dark blue.jpg + GT: [dark blue] + VLM: [navy blue] (2 jersey(s), 7.5s) + PASS similar:1 + +[4/161] 004 - purple_light blue.jpg + GT: [purple, light blue] + VLM: [light blue, purple] (3 jersey(s), 18.8s) + PASS exact:2 + +[5/161] 005 - white or gray_purple.jpg + GT: [gray, purple] + VLM: [purple] (1 jersey(s), 3.7s) + PARTIAL exact:1, MISS:gray + +[6/161] 006 - navy blue.jpg + GT: [navy blue] + VLM: [dark blue] (1 jersey(s), 4.7s) + PASS similar:1 + +[7/161] 007 - brown_white.jpg + GT: [brown] + VLM: [brown] (2 jersey(s), 6.3s) + PASS exact:1 + +[8/161] 008 -red or orange.jpg + GT: [red|orange] + VLM: [red] (1 jersey(s), 7.5s) + PASS exact:1 + +[9/161] 009 - white_red.jpg + GT: [red] + VLM: [red] (3 jersey(s), 12.1s) + PASS exact:1 + +[10/161] 010 - white_black.jpg + GT: [black] + VLM: [black] (3 jersey(s), 13.8s) + PASS exact:1 + +[11/161] 011 - white or gray_purple.jpg + GT: [gray, purple] + VLM: [purple] (4 jersey(s), 12.5s) + PARTIAL exact:1, MISS:gray + +[12/161] 012 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 3.5s) + PASS exact:1 + +[13/161] 013 - light blue.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 4.1s) + PASS exact:1 + +[14/161] 014 - orange_dark blue or purple.jpg + GT: [orange, dark blue|purple] + VLM: [orange, purple] (3 jersey(s), 4.6s) + PASS exact:2 + +[15/161] 015 - green.jpg + GT: [green] + VLM: [green] (2 jersey(s), 4.0s) + PASS exact:1 + +[16/161] 016 - maroon.jpg + GT: [maroon] + VLM: [(none)] (0 jersey(s), 5.0s) + FAIL MISS:maroon + +[17/161] 017 - brown_white.jpg + GT: [brown] + VLM: [brown] (3 jersey(s), 8.9s) + PASS exact:1 + +[18/161] 018 - gray_red.jpg + GT: [gray, red] + VLM: [grey] (1 jersey(s), 4.1s) + PARTIAL similar:1, MISS:red + +[19/161] 019 - maroon_gold.jpg + GT: [maroon, gold] + VLM: [red] (1 jersey(s), 5.0s) + FAIL MISS:maroon,gold, extra:red + +[20/161] 020 - white_brown or orange.jpg + GT: [brown|orange] + VLM: [orange] (2 jersey(s), 4.0s) + PASS exact:1 + +[21/161] 021 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 4.3s) + PASS exact:1 + +[22/161] 022 - black_light blue.jpg + GT: [black, light blue] + VLM: [light blue] (1 jersey(s), 5.3s) + PARTIAL exact:1, MISS:black + +[23/161] 023 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 3.6s) + PASS exact:1 + +[24/161] 024 - white_pink.jpg + GT: [pink] + VLM: [pink] (2 jersey(s), 3.6s) + PASS exact:1 + +[25/161] 025 - blue_green.jpg + GT: [blue, green] + VLM: [green] (1 jersey(s), 3.3s) + PARTIAL exact:1, MISS:blue + +[26/161] 026 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 5.9s) + PASS exact:1 + +[27/161] 027 - red_white.jpg + GT: [red] + VLM: [red] (4 jersey(s), 36.1s) + PASS exact:1 + +[28/161] 028 - green_white.jpg + GT: [green] + VLM: [green] (5 jersey(s), 38.3s) + PASS exact:1 + +[29/161] 029 -maroon_white.jpg + GT: [maroon] + VLM: [red] (2 jersey(s), 4.8s) + FAIL MISS:maroon, extra:red + +[30/161] 030 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (2 jersey(s), 10.8s) + PASS similar:1 + +[31/161] 031 - brown_white.jpg + GT: [brown] + VLM: [brown] (2 jersey(s), 4.2s) + PASS exact:1 + +[32/161] 032 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 4.8s) + PASS exact:1 + +[33/161] 033 - navy blue_white or gray.jpg + GT: [navy blue, gray] + VLM: [blue] (7 jersey(s), 40.2s) + PARTIAL similar:1, MISS:gray + +[34/161] 034 - light blue.jpg + GT: [light blue] + VLM: [blue] (1 jersey(s), 12.7s) + FAIL MISS:light blue, extra:blue + +[35/161] 035 -green_gold or yellow.jpg + GT: [green, gold|yellow] + VLM: [green, yellow] (3 jersey(s), 9.2s) + PASS exact:2 + +[36/161] 036 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (4 jersey(s), 5.0s) + PASS exact:1 + +[37/161] 037 -navy_white.jpg + GT: [navy] + VLM: [blue] (4 jersey(s), 7.5s) + PASS similar:1 + +[38/161] 038 - red_white.jpg + GT: [red] + VLM: [red] (3 jersey(s), 36.8s) + PASS exact:1 + +[39/161] 039 - gray_white.jpg + GT: [gray] + VLM: [blue, grey] (4 jersey(s), 38.9s) + PARTIAL similar:1, extra:blue + +[40/161] 040 - maroon_gray.jpg + GT: [maroon, gray] + VLM: [grey, maroon] (2 jersey(s), 11.3s) + PASS exact:1, similar:1 + +[41/161] 041 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (8 jersey(s), 7.2s) + PASS similar:1 + +[42/161] 042 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 3.5s) + PASS exact:1 + +[43/161] 043 - gray_black.jpg + GT: [gray, black] + VLM: [black, grey] (5 jersey(s), 7.6s) + PASS exact:1, similar:1 + +[44/161] 044 - purple_black.jpg + GT: [purple, black] + VLM: [purple] (8 jersey(s), 36.8s) + PARTIAL exact:1, MISS:black + +[45/161] 045 - purple.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 5.4s) + PASS exact:1 + +[46/161] 046 - green.jpg + GT: [green] + VLM: [black] (8 jersey(s), 39.3s) + FAIL MISS:green, extra:black + +[47/161] 047 - purple_white.jpg + GT: [purple] + VLM: [purple] (3 jersey(s), 4.7s) + PASS exact:1 + +[48/161] 048 - red.jpg + GT: [red] + VLM: [(none)] (0 jersey(s), 34.4s) + FAIL MISS:red + +[49/161] 049 - white_gold.jpg + GT: [gold] + VLM: [yellow] (2 jersey(s), 4.1s) + PASS similar:1 + +[50/161] 050 - white_orange.jpg + GT: [orange] + VLM: [orange] (5 jersey(s), 37.3s) + PASS exact:1 + +[51/161] 051 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 3.2s) + PASS exact:1 + +[52/161] 052 - black_gold.jpg + GT: [black, gold] + VLM: [black] (1 jersey(s), 3.7s) + PARTIAL exact:1, MISS:gold + +[53/161] 053 - black_white.jpg + GT: [black] + VLM: [(none)] (1 jersey(s), 3.4s) + FAIL MISS:black + +[54/161] 054 - white_blue.jpg + GT: [blue] + VLM: [blue] (2 jersey(s), 3.3s) + PASS exact:1 + +[55/161] 055 - green_gold.jpg + GT: [green, gold] + VLM: [green] (1 jersey(s), 11.1s) + PARTIAL exact:1, MISS:gold + +[56/161] 056 - white_red.jpg + GT: [red] + VLM: [red] (3 jersey(s), 6.6s) + PASS exact:1 + +[57/161] 057 - white_gold or yellow.jpg + GT: [gold|yellow] + VLM: [(none)] (1 jersey(s), 4.0s) + FAIL MISS:gold|yellow + +[58/161] 058 - purple.jpg + GT: [purple] + VLM: [purple] (4 jersey(s), 7.7s) + PASS exact:1 + +[59/161] 059 - black_gold.jpg + GT: [black, gold] + VLM: [gold] (1 jersey(s), 4.3s) + PARTIAL exact:1, MISS:black + +[60/161] 060 - gray_navy blue.jpg + GT: [gray, navy blue] + VLM: [blue] (2 jersey(s), 4.8s) + PARTIAL similar:1, MISS:gray + +[61/161] 061 - brown or orange.jpg + GT: [brown|orange] + VLM: [orange] (1 jersey(s), 4.0s) + PASS exact:1 + +[62/161] 062 - orange_blue.jpg + GT: [orange, blue] + VLM: [blue, orange] (2 jersey(s), 4.3s) + PASS exact:2 + +[63/161] 063 - dark brown.jpg + GT: [dark brown] + VLM: [brown] (1 jersey(s), 3.5s) + PASS similar:1 + +[64/161] 064 - green_white.jpg + GT: [green] + VLM: [green] (1 jersey(s), 5.7s) + PASS exact:1 + +[65/161] 065 - green_gold.jpg + GT: [green, gold] + VLM: [green, yellow] (5 jersey(s), 40.7s) + PASS exact:1, similar:1 + +[66/161] 066 - yellow.jpg + GT: [yellow] + VLM: [yellow] (1 jersey(s), 4.7s) + PASS exact:1 + +[67/161] 067 - red_white.jpg + GT: [red] + VLM: [red] (5 jersey(s), 5.8s) + PASS exact:1 + +[68/161] 068 - gold.jpg + GT: [gold] + VLM: [gold] (1 jersey(s), 4.3s) + PASS exact:1 + +[69/161] 069 - red_white.jpg + GT: [red] + VLM: [(none)] (5 jersey(s), 38.2s) + FAIL MISS:red + +[70/161] 070 - green_white.jpg + GT: [green] + VLM: [green] (3 jersey(s), 6.2s) + PASS exact:1 + +[71/161] 071 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 3.8s) + PASS exact:1 + +[72/161] 072 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 3.5s) + PASS exact:1 + +[73/161] 073 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (1 jersey(s), 9.0s) + PASS exact:1 + +[74/161] 074 - white_orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 4.3s) + PASS exact:1 + +[75/161] 075 - green_white.jpg + GT: [green] + VLM: [green] (1 jersey(s), 3.2s) + PASS exact:1 + +[76/161] 076 - light blue_white.jpg + GT: [light blue] + VLM: [light blue, pink] (4 jersey(s), 8.1s) + PARTIAL exact:1, extra:pink + +[77/161] 077 - teal_white.jpg + GT: [teal] + VLM: [green] (5 jersey(s), 37.1s) + FAIL MISS:teal, extra:green + +[78/161] 078 - light blue_white.jpg + GT: [light blue] + VLM: [blue] (2 jersey(s), 10.8s) + FAIL MISS:light blue, extra:blue + +[79/161] 079 - blue_maroon.jpg + GT: [blue, maroon] + VLM: [blue, red] (6 jersey(s), 36.8s) + PARTIAL exact:1, MISS:maroon, extra:red + +[80/161] 080 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (1 jersey(s), 3.4s) + PASS similar:1 + +[81/161] 081 - navy blue.jpg + GT: [navy blue] + VLM: [blue] (2 jersey(s), 3.9s) + PASS similar:1 + +[82/161] 082 - dark blue_white.jpg + GT: [dark blue] + VLM: [navy blue] (3 jersey(s), 6.3s) + PASS similar:1 + +[83/161] 083 - dark brown_white.jpg + GT: [dark brown] + VLM: [black] (2 jersey(s), 14.2s) + FAIL MISS:dark brown, extra:black + +[84/161] 084 - dark brown_yellow.jpg + GT: [dark brown, yellow] + VLM: [brown, yellow] (2 jersey(s), 3.8s) + PASS exact:1, similar:1 + +[85/161] 085 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.3s) + PASS exact:1 + +[86/161] 086 - dark brown_white.jpg + GT: [dark brown] + VLM: [brown] (1 jersey(s), 4.5s) + PASS similar:1 + +[87/161] 087 - white_light blue.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 7.5s) + PASS exact:1 + +[88/161] 088 - white_maroon.jpg + GT: [maroon] + VLM: [maroon] (4 jersey(s), 41.4s) + PASS exact:1 + +[89/161] 089 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 5.8s) + PASS exact:1 + +[90/161] 090 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (5 jersey(s), 38.4s) + PASS exact:1 + +[91/161] 091 - teal.jpg + GT: [teal] + VLM: [teal] (3 jersey(s), 10.2s) + PASS exact:1 + +[92/161] 092 - green_white.jpg + GT: [green] + VLM: [green] (5 jersey(s), 39.3s) + PASS exact:1 + +[93/161] 093 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (2 jersey(s), 4.6s) + PASS similar:1 + +[94/161] 094 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 7.0s) + PASS exact:1 + +[95/161] 095 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 22.9s) + PASS exact:1 + +[96/161] 096 - orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 5.2s) + PASS exact:1 + +[97/161] 097 - gray_black.jpg + GT: [gray, black] + VLM: [grey] (2 jersey(s), 19.4s) + PARTIAL similar:1, MISS:black + +[98/161] 098 - teal_white.jpg + GT: [teal] + VLM: [teal] (2 jersey(s), 4.3s) + PASS exact:1 + +[99/161] 099 - maroon_white.jpg + GT: [maroon] + VLM: [red] (3 jersey(s), 4.5s) + FAIL MISS:maroon, extra:red + +[100/161] 100 - orange_white.jpg + GT: [orange] + VLM: [orange] (4 jersey(s), 40.0s) + PASS exact:1 + +[101/161] 101 - green_white.jpg + GT: [green] + VLM: [green] (7 jersey(s), 39.2s) + PASS exact:1 + +[102/161] 102 - yellow-black.jpg + GT: [yellow, black] + VLM: [black] (1 jersey(s), 4.2s) + PARTIAL exact:1, MISS:yellow + +[103/161] 103 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 36.3s) + PASS exact:1 + +[104/161] 104 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 4.1s) + PASS exact:1 + +[105/161] 105 - orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 6.3s) + PASS exact:1 + +[106/161] 106 - black_gray.jpg + GT: [black, gray] + VLM: [black, grey] (2 jersey(s), 4.0s) + PASS exact:1, similar:1 + +[107/161] 107 - orange_white.jpg + GT: [orange] + VLM: [orange] (3 jersey(s), 4.4s) + PASS exact:1 + +[108/161] 108 - red_white.jpg + GT: [red] + VLM: [red] (1 jersey(s), 47.1s) + PASS exact:1 + +[109/161] 109 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 5.2s) + PASS exact:1 + +[110/161] 110 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 10.7s) + PASS exact:1 + +[111/161] 111 - orange_white.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 34.8s) + PASS exact:1 + +[112/161] 112 - orange_white.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 5.8s) + PASS exact:1 + +[113/161] 113 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 5.1s) + PASS exact:1 + +[114/161] 114 - black_white.jpg + GT: [black] + VLM: [black] (2 jersey(s), 5.7s) + PASS exact:1 + +[115/161] 115 - navy blue_maroon.jpg + GT: [navy blue, maroon] + VLM: [blue, red] (4 jersey(s), 7.9s) + PARTIAL similar:1, MISS:maroon, extra:red + +[116/161] 116 - gray_white.jpg + GT: [gray] + VLM: [grey] (2 jersey(s), 3.9s) + PASS similar:1 + +[117/161] 117 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 3.8s) + PASS exact:1 + +[118/161] 118 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (1 jersey(s), 8.5s) + PASS similar:1 + +[119/161] 119 - black_yellow.jpg + GT: [black, yellow] + VLM: [black, yellow] (3 jersey(s), 4.7s) + PASS exact:2 + +[120/161] 120 - red_dark blue.jpg + GT: [red, dark blue] + VLM: [dark blue, red] (3 jersey(s), 7.0s) + PASS exact:2 + +[121/161] 121 - orange_white.jpg + GT: [orange] + VLM: [orange] (3 jersey(s), 5.9s) + PASS exact:1 + +[122/161] 122 - gray.jpg + GT: [gray] + VLM: [grey] (1 jersey(s), 2.6s) + PASS similar:1 + +[123/161] 123 - teal_white.jpg + GT: [teal] + VLM: [teal] (4 jersey(s), 8.8s) + PASS exact:1 + +[124/161] 124 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (4 jersey(s), 4.9s) + PASS similar:1 + +[125/161] 125 - dark blue_maroon.jpg + GT: [dark blue, maroon] + VLM: [navy, red] (3 jersey(s), 8.1s) + PARTIAL similar:1, MISS:maroon, extra:red + +[126/161] 126 - white_blue.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 5.8s) + PASS exact:1 + +[127/161] 127 - yellow.jpg + GT: [yellow] + VLM: [yellow] (4 jersey(s), 4.8s) + PASS exact:1 + +[128/161] 128 - green_white.jpg + GT: [green] + VLM: [(none)] (0 jersey(s), 42.6s) + FAIL MISS:green + +[129/161] 129 - blue_white.jpg + GT: [blue] + VLM: [(none)] (3 jersey(s), 16.8s) + FAIL MISS:blue + +[130/161] 130 - yellow_black.jpg + GT: [yellow, black] + VLM: [yellow] (1 jersey(s), 3.4s) + PARTIAL exact:1, MISS:black + +[131/161] 131 - purple_orange.jpg + GT: [purple, orange] + VLM: [orange, purple] (3 jersey(s), 3.8s) + PASS exact:2 + +[132/161] 132 - brown_white.jpg + GT: [brown] + VLM: [orange] (2 jersey(s), 10.2s) + FAIL MISS:brown, extra:orange + +[133/161] 133 - light blue.png + GT: [light blue] + VLM: [light blue] (8 jersey(s), 43.5s) + PASS exact:1 + +[134/161] 134 - teal_white.jpg + GT: [teal] + VLM: [light blue] (1 jersey(s), 4.3s) + FAIL MISS:teal, extra:light blue + +[135/161] 135 - green.jpg + GT: [green] + VLM: [green] (1 jersey(s), 5.2s) + PASS exact:1 + +[136/161] 136 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 3.8s) + PASS exact:1 + +[137/161] 137 - green_white.jpg + GT: [green] + VLM: [green] (3 jersey(s), 8.6s) + PASS exact:1 + +[138/161] 138 - maroon.jpg + GT: [maroon] + VLM: [red] (1 jersey(s), 3.3s) + FAIL MISS:maroon, extra:red + +[139/161] 139 - dark blue_white.jpg + GT: [dark blue] + VLM: [blue] (1 jersey(s), 4.8s) + PASS similar:1 + +[140/161] 140 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 3.5s) + PASS exact:1 + +[141/161] 141 - light blue_white.jpg + GT: [light blue] + VLM: [blue] (3 jersey(s), 5.2s) + FAIL MISS:light blue, extra:blue + +[142/161] 142 - orange_white.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 5.5s) + PASS exact:1 + +[143/161] 143 - blue_white.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 4.7s) + PASS exact:1 + +[144/161] 144 - green.jpg + GT: [green] + VLM: [green] (8 jersey(s), 39.7s) + PASS exact:1 + +[145/161] 145 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 3.8s) + PASS exact:1 + +[146/161] 146 - red_gray.jpg + GT: [red, gray] + VLM: [grey, red] (2 jersey(s), 4.0s) + PASS exact:1, similar:1 + +[147/161] 147 - green.jpg + GT: [green] + VLM: [green] (3 jersey(s), 4.1s) + PASS exact:1 + +[148/161] 148 - yellow_purple.jpg + GT: [yellow, purple] + VLM: [purple, yellow] (2 jersey(s), 5.9s) + PASS exact:2 + +[149/161] 149 - blue_white.jpg + GT: [blue] + VLM: [blue] (5 jersey(s), 36.9s) + PASS exact:1 + +[150/161] 150 - green_gray.jpg + GT: [green, gray] + VLM: [black] (1 jersey(s), 12.8s) + FAIL MISS:green,gray, extra:black + +[151/161] 151 - yellow_black.jpg + GT: [yellow, black] + VLM: [dark blue, yellow] (5 jersey(s), 38.6s) + PARTIAL exact:1, MISS:black, extra:dark blue + +[152/161] 152 - pink_dark blue.jpg + GT: [pink, dark blue] + VLM: [navy blue, pink] (3 jersey(s), 22.1s) + PASS exact:1, similar:1 + +[153/161] 153 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 3.7s) + PASS exact:1 + +[154/161] 154 - dark brown.jpeg + GT: [dark brown] + VLM: [brown] (5 jersey(s), 5.1s) + PASS similar:1 + +[155/161] 155 - white_green_gray_purple_yellow.jpg + GT: [green, gray, purple, yellow] + VLM: [grey, purple, yellow] (5 jersey(s), 7.4s) + PARTIAL exact:2, similar:1, MISS:green + +[156/161] 156 - maroon_gray.jpg + GT: [maroon, gray] + VLM: [maroon] (1 jersey(s), 12.0s) + PARTIAL exact:1, MISS:gray + +[157/161] 157 - blue_white.jpg + GT: [blue] + VLM: [blue] (4 jersey(s), 38.1s) + PASS exact:1 + +[158/161] 158 - dark blue_yellow.jpg + GT: [dark blue, yellow] + VLM: [blue, yellow] (7 jersey(s), 37.4s) + PASS exact:1, similar:1 + +[159/161] 159 - blue_white.jpg + GT: [blue] + VLM: [blue] (5 jersey(s), 11.2s) + PASS exact:1 + +[160/161] 160 - blue_white.jpg + GT: [blue] + VLM: [(none)] (1 jersey(s), 4.2s) + FAIL MISS:blue + +[161/161] 161 - light blue_white.jpg + GT: [light blue] + VLM: [blue] (2 jersey(s), 5.6s) + FAIL MISS:light blue, extra:blue + +================================================================================ +ACCURACY SUMMARY (gemini-3-flash-preview) +================================================================================ +Images processed: 161 +Errors: 0 +Total time: 259.8s (1.6s avg) + +Ground truth colors: 202 (excluding white) +VLM unique colors: 177 (excluding white) + +--- Recall (did VLM find each ground truth color?) --- + Exact match: 123 / 202 (60.9%) + Similar match: 35 / 202 (17.3%) + Total found: 158 / 202 (78.2%) + Missed: 44 / 202 (21.8%) + +--- Precision (are VLM colors correct?) --- + Exact match: 123 / 177 (69.5%) + Similar match: 34 / 177 (19.2%) + Total correct: 157 / 177 (88.7%) + Extra/wrong: 20 / 177 (11.3%) + +--- Similar-Match Confusions (expected -> got) --- + gray -> grey x10 + navy blue -> blue x7 + dark brown -> brown x5 + dark blue -> blue x5 + dark blue -> navy blue x3 + gold -> yellow x2 + navy blue -> dark blue x1 + navy -> blue x1 + dark blue -> navy x1 + +--- Most Missed Ground Truth Colors --- + maroon 8 ######## + black 7 ####### + gray 6 ###### + light blue 4 #### + green 4 #### + red 3 ### + gold 3 ### + blue 3 ### + teal 2 ## + gold|yellow 1 # + dark brown 1 # + yellow 1 # + brown 1 # + +--- Most Common Extra/Wrong VLM Colors --- + red 7 ####### + blue 5 ##### + black 3 ### + pink 1 # + green 1 # + orange 1 # + light blue 1 # + dark blue 1 # + +--- Per-Image Verdict --- + PASS 117 + PARTIAL 22 + FAIL 22 + +--- Failed Images (22) --- + 016 - maroon.jpg + missed: maroon + 019 - maroon_gold.jpg + missed: maroon, gold + extra: red + 029 -maroon_white.jpg + missed: maroon + extra: red + 034 - light blue.jpg + missed: light blue + extra: blue + 046 - green.jpg + missed: green + extra: black + 048 - red.jpg + missed: red + 053 - black_white.jpg + missed: black + 057 - white_gold or yellow.jpg + missed: gold|yellow + 069 - red_white.jpg + missed: red + 077 - teal_white.jpg + missed: teal + extra: green + 078 - light blue_white.jpg + missed: light blue + extra: blue + 083 - dark brown_white.jpg + missed: dark brown + extra: black + 099 - maroon_white.jpg + missed: maroon + extra: red + 128 - green_white.jpg + missed: green + 129 - blue_white.jpg + missed: blue + 132 - brown_white.jpg + missed: brown + extra: orange + 134 - teal_white.jpg + missed: teal + extra: light blue + 138 - maroon.jpg + missed: maroon + extra: red + 141 - light blue_white.jpg + missed: light blue + extra: blue + 150 - green_gray.jpg + missed: green, gray + extra: black + 160 - blue_white.jpg + missed: blue + 161 - light blue_white.jpg + missed: light blue + extra: blue + +======================================== +Qwen3-VL-8B + jersey_prompt_constrained.txt +Started: Tue Mar 3 05:39:17 PM MST 2026 +======================================== +Images to process: 161 +Server: http://agx:8080 +Prompt: /home/rmcewen/data/dev.python/jersey_test/jersey_prompt_constrained.txt (2223 chars) +================================================================================ + +[1/161] 001 -brown_white or dark brown.jpg + GT: [brown, dark brown] + VLM: [black] (3 jersey(s), 11.6s) + FAIL MISS:brown,dark brown, extra:black + +[2/161] 002 - yellow.jpg + GT: [yellow] + VLM: [yellow] (2 jersey(s), 8.0s) + PASS exact:1 + +[3/161] 003 - dark blue.jpg + GT: [dark blue] + VLM: [dark blue] (3 jersey(s), 11.1s) + PASS exact:1 + +[4/161] 004 - purple_light blue.jpg + GT: [purple, light blue] + VLM: [light blue, purple] (3 jersey(s), 11.7s) + PASS exact:2 + +[5/161] 005 - white or gray_purple.jpg + GT: [gray, purple] + VLM: [purple] (1 jersey(s), 5.0s) + PARTIAL exact:1, MISS:gray + +[6/161] 006 - navy blue.jpg + GT: [navy blue] + VLM: [dark blue] (1 jersey(s), 4.4s) + PASS similar:1 + +[7/161] 007 - brown_white.jpg + GT: [brown] + VLM: [maroon] (2 jersey(s), 8.0s) + FAIL MISS:brown, extra:maroon + +[8/161] 008 -red or orange.jpg + GT: [red|orange] + VLM: [red] (1 jersey(s), 4.3s) + PASS exact:1 + +[9/161] 009 - white_red.jpg + GT: [red] + VLM: [gold, red] (3 jersey(s), 10.8s) + PARTIAL exact:1, extra:gold + +[10/161] 010 - white_black.jpg + GT: [black] + VLM: [black, maroon] (3 jersey(s), 11.0s) + PARTIAL exact:1, extra:maroon + +[11/161] 011 - white or gray_purple.jpg + GT: [gray, purple] + VLM: [purple] (4 jersey(s), 13.8s) + PARTIAL exact:1, MISS:gray + +[12/161] 012 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 7.3s) + PASS exact:1 + +[13/161] 013 - light blue.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 7.6s) + PASS exact:1 + +[14/161] 014 - orange_dark blue or purple.jpg + GT: [orange, dark blue|purple] + VLM: [orange, purple] (3 jersey(s), 11.0s) + PASS exact:2 + +[15/161] 015 - green.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.3s) + PASS exact:1 + +[16/161] 016 - maroon.jpg + GT: [maroon] + VLM: [(none)] (0 jersey(s), 1.7s) + FAIL MISS:maroon + +[17/161] 017 - brown_white.jpg + GT: [brown] + VLM: [dark brown] (2 jersey(s), 8.8s) + PASS similar:1 + +[18/161] 018 - gray_red.jpg + GT: [gray, red] + VLM: [gray, red] (2 jersey(s), 7.3s) + PASS exact:2 + +[19/161] 019 - maroon_gold.jpg + GT: [maroon, gold] + VLM: [maroon, yellow] (2 jersey(s), 7.8s) + PASS exact:1, similar:1 + +[20/161] 020 - white_brown or orange.jpg + GT: [brown|orange] + VLM: [orange] (2 jersey(s), 8.1s) + PASS exact:1 + +[21/161] 021 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 8.0s) + PASS exact:1 + +[22/161] 022 - black_light blue.jpg + GT: [black, light blue] + VLM: [light blue] (1 jersey(s), 5.0s) + PARTIAL exact:1, MISS:black + +[23/161] 023 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 7.7s) + PASS exact:1 + +[24/161] 024 - white_pink.jpg + GT: [pink] + VLM: [pink] (2 jersey(s), 7.7s) + PASS exact:1 + +[25/161] 025 - blue_green.jpg + GT: [blue, green] + VLM: [green] (1 jersey(s), 4.3s) + PARTIAL exact:1, MISS:blue + +[26/161] 026 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.9s) + PASS exact:1 + +[27/161] 027 - red_white.jpg + GT: [red] + VLM: [red] (5 jersey(s), 16.1s) + PASS exact:1 + +[28/161] 028 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.9s) + PASS exact:1 + +[29/161] 029 -maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 8.0s) + PASS exact:1 + +[30/161] 030 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (2 jersey(s), 7.8s) + PASS similar:1 + +[31/161] 031 - brown_white.jpg + GT: [brown] + VLM: [maroon] (2 jersey(s), 7.9s) + FAIL MISS:brown, extra:maroon + +[32/161] 032 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 8.1s) + PASS exact:1 + +[33/161] 033 - navy blue_white or gray.jpg + GT: [navy blue, gray] + VLM: [blue] (3 jersey(s), 10.9s) + PARTIAL similar:1, MISS:gray + +[34/161] 034 - light blue.jpg + GT: [light blue] + VLM: [blue] (1 jersey(s), 4.8s) + FAIL MISS:light blue, extra:blue + +[35/161] 035 -green_gold or yellow.jpg + GT: [green, gold|yellow] + VLM: [green, yellow] (2 jersey(s), 8.0s) + PASS exact:2 + +[36/161] 036 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (4 jersey(s), 14.0s) + PASS exact:1 + +[37/161] 037 -navy_white.jpg + GT: [navy] + VLM: [dark blue] (3 jersey(s), 10.3s) + PASS similar:1 + +[38/161] 038 - red_white.jpg + GT: [red] + VLM: [red] (3 jersey(s), 10.9s) + PASS exact:1 + +[39/161] 039 - gray_white.jpg + GT: [gray] + VLM: [gray] (2 jersey(s), 7.9s) + PASS exact:1 + +[40/161] 040 - maroon_gray.jpg + GT: [maroon, gray] + VLM: [maroon] (1 jersey(s), 5.1s) + PARTIAL exact:1, MISS:gray + +[41/161] 041 - navy blue_white.jpg + GT: [navy blue] + VLM: [navy blue] (9 jersey(s), 30.6s) + PASS exact:1 + +[42/161] 042 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 4.9s) + PASS exact:1 + +[43/161] 043 - gray_black.jpg + GT: [gray, black] + VLM: [black, gray] (2 jersey(s), 8.0s) + PASS exact:2 + +[44/161] 044 - purple_black.jpg + GT: [purple, black] + VLM: [purple] (7 jersey(s), 22.6s) + PARTIAL exact:1, MISS:black + +[45/161] 045 - purple.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 7.8s) + PASS exact:1 + +[46/161] 046 - green.jpg + GT: [green] + VLM: [black] (15 jersey(s), 46.5s) + FAIL MISS:green, extra:black + +[47/161] 047 - purple_white.jpg + GT: [purple] + VLM: [purple] (3 jersey(s), 10.8s) + PASS exact:1 + +[48/161] 048 - red.jpg + GT: [red] + VLM: [maroon] (1 jersey(s), 5.0s) + FAIL MISS:red, extra:maroon + +[49/161] 049 - white_gold.jpg + GT: [gold] + VLM: [yellow] (2 jersey(s), 7.9s) + PASS similar:1 + +[50/161] 050 - white_orange.jpg + GT: [orange] + VLM: [orange] (4 jersey(s), 14.1s) + PASS exact:1 + +[51/161] 051 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 4.9s) + PASS exact:1 + +[52/161] 052 - black_gold.jpg + GT: [black, gold] + VLM: [black, yellow] (2 jersey(s), 7.8s) + PASS exact:1, similar:1 + +[53/161] 053 - black_white.jpg + GT: [black] + VLM: [(none)] (1 jersey(s), 4.9s) + FAIL MISS:black + +[54/161] 054 - white_blue.jpg + GT: [blue] + VLM: [navy blue] (2 jersey(s), 8.1s) + PASS similar:1 + +[55/161] 055 - green_gold.jpg + GT: [green, gold] + VLM: [green, yellow] (2 jersey(s), 7.8s) + PASS exact:1, similar:1 + +[56/161] 056 - white_red.jpg + GT: [red] + VLM: [red] (2 jersey(s), 7.9s) + PASS exact:1 + +[57/161] 057 - white_gold or yellow.jpg + GT: [gold|yellow] + VLM: [(none)] (1 jersey(s), 4.9s) + FAIL MISS:gold|yellow + +[58/161] 058 - purple.jpg + GT: [purple] + VLM: [purple] (4 jersey(s), 14.0s) + PASS exact:1 + +[59/161] 059 - black_gold.jpg + GT: [black, gold] + VLM: [gold] (1 jersey(s), 4.9s) + PARTIAL exact:1, MISS:black + +[60/161] 060 - gray_navy blue.jpg + GT: [gray, navy blue] + VLM: [blue] (2 jersey(s), 8.1s) + PARTIAL similar:1, MISS:gray + +[61/161] 061 - brown or orange.jpg + GT: [brown|orange] + VLM: [orange] (2 jersey(s), 7.8s) + PASS exact:1 + +[62/161] 062 - orange_blue.jpg + GT: [orange, blue] + VLM: [blue, orange] (2 jersey(s), 7.5s) + PASS exact:2 + +[63/161] 063 - dark brown.jpg + GT: [dark brown] + VLM: [dark brown] (1 jersey(s), 5.0s) + PASS exact:1 + +[64/161] 064 - green_white.jpg + GT: [green] + VLM: [green] (3 jersey(s), 10.7s) + PASS exact:1 + +[65/161] 065 - green_gold.jpg + GT: [green, gold] + VLM: [dark green, yellow] (3 jersey(s), 10.6s) + PASS similar:2 + +[66/161] 066 - yellow.jpg + GT: [yellow] + VLM: [yellow] (1 jersey(s), 4.8s) + PASS exact:1 + +[67/161] 067 - red_white.jpg + GT: [red] + VLM: [red] (4 jersey(s), 13.7s) + PASS exact:1 + +[68/161] 068 - gold.jpg + GT: [gold] + VLM: [gold] (1 jersey(s), 4.8s) + PASS exact:1 + +[69/161] 069 - red_white.jpg + GT: [red] + VLM: [(none)] (4 jersey(s), 14.1s) + FAIL MISS:red + +[70/161] 070 - green_white.jpg + GT: [green] + VLM: [green] (3 jersey(s), 11.1s) + PASS exact:1 + +[71/161] 071 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 8.0s) + PASS exact:1 + +[72/161] 072 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 7.5s) + PASS exact:1 + +[73/161] 073 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 7.4s) + PASS exact:1 + +[74/161] 074 - white_orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 7.5s) + PASS exact:1 + +[75/161] 075 - green_white.jpg + GT: [green] + VLM: [green] (3 jersey(s), 10.7s) + PASS exact:1 + +[76/161] 076 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (3 jersey(s), 11.4s) + PASS exact:1 + +[77/161] 077 - teal_white.jpg + GT: [teal] + VLM: [green] (4 jersey(s), 13.4s) + FAIL MISS:teal, extra:green + +[78/161] 078 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 7.7s) + PASS exact:1 + +[79/161] 079 - blue_maroon.jpg + GT: [blue, maroon] + VLM: [blue, maroon] (4 jersey(s), 14.1s) + PASS exact:2 + +[80/161] 080 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (2 jersey(s), 7.8s) + PASS similar:1 + +[81/161] 081 - navy blue.jpg + GT: [navy blue] + VLM: [blue] (2 jersey(s), 7.7s) + PASS similar:1 + +[82/161] 082 - dark blue_white.jpg + GT: [dark blue] + VLM: [dark blue] (3 jersey(s), 10.8s) + PASS exact:1 + +[83/161] 083 - dark brown_white.jpg + GT: [dark brown] + VLM: [black] (2 jersey(s), 7.9s) + FAIL MISS:dark brown, extra:black + +[84/161] 084 - dark brown_yellow.jpg + GT: [dark brown, yellow] + VLM: [dark brown, gold] (2 jersey(s), 8.0s) + PASS exact:1, similar:1 + +[85/161] 085 - green_white.jpg + GT: [green] + VLM: [green] (1 jersey(s), 4.8s) + PASS exact:1 + +[86/161] 086 - dark brown_white.jpg + GT: [dark brown] + VLM: [dark brown] (2 jersey(s), 8.0s) + PASS exact:1 + +[87/161] 087 - white_light blue.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 8.0s) + PASS exact:1 + +[88/161] 088 - white_maroon.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 7.8s) + PASS exact:1 + +[89/161] 089 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 11.1s) + PASS exact:1 + +[90/161] 090 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (4 jersey(s), 14.3s) + PASS exact:1 + +[91/161] 091 - teal.jpg + GT: [teal] + VLM: [teal] (2 jersey(s), 8.0s) + PASS exact:1 + +[92/161] 092 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 14.0s) + PASS exact:1 + +[93/161] 093 - dark blue_white.jpg + GT: [dark blue] + VLM: [navy blue] (2 jersey(s), 8.1s) + PASS similar:1 + +[94/161] 094 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 12.5s) + PASS exact:1 + +[95/161] 095 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 8.0s) + PASS exact:1 + +[96/161] 096 - orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 8.6s) + PASS exact:1 + +[97/161] 097 - gray_black.jpg + GT: [gray, black] + VLM: [light blue] (2 jersey(s), 8.3s) + FAIL MISS:gray,black, extra:light blue + +[98/161] 098 - teal_white.jpg + GT: [teal] + VLM: [teal] (2 jersey(s), 8.7s) + PASS exact:1 + +[99/161] 099 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 12.2s) + PASS exact:1 + +[100/161] 100 - orange_white.jpg + GT: [orange] + VLM: [orange] (4 jersey(s), 13.8s) + PASS exact:1 + +[101/161] 101 - green_white.jpg + GT: [green] + VLM: [green] (5 jersey(s), 17.0s) + PASS exact:1 + +[102/161] 102 - yellow-black.jpg + GT: [yellow, black] + VLM: [black, yellow] (2 jersey(s), 8.0s) + PASS exact:2 + +[103/161] 103 - green_white.jpg + GT: [green] + VLM: [green] (5 jersey(s), 17.3s) + PASS exact:1 + +[104/161] 104 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 8.0s) + PASS exact:1 + +[105/161] 105 - orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 9.2s) + PASS exact:1 + +[106/161] 106 - black_gray.jpg + GT: [black, gray] + VLM: [black, gray] (2 jersey(s), 9.1s) + PASS exact:2 + +[107/161] 107 - orange_white.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 7.7s) + PASS exact:1 + +[108/161] 108 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 8.0s) + PASS exact:1 + +[109/161] 109 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 7.8s) + PASS exact:1 + +[110/161] 110 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 14.0s) + PASS exact:1 + +[111/161] 111 - orange_white.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 7.9s) + PASS exact:1 + +[112/161] 112 - orange_white.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 7.8s) + PASS exact:1 + +[113/161] 113 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 4.9s) + PASS exact:1 + +[114/161] 114 - black_white.jpg + GT: [black] + VLM: [black] (2 jersey(s), 8.1s) + PASS exact:1 + +[115/161] 115 - navy blue_maroon.jpg + GT: [navy blue, maroon] + VLM: [blue, maroon] (4 jersey(s), 14.0s) + PASS exact:1, similar:1 + +[116/161] 116 - gray_white.jpg + GT: [gray] + VLM: [gray] (2 jersey(s), 8.0s) + PASS exact:1 + +[117/161] 117 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 8.1s) + PASS exact:1 + +[118/161] 118 - dark blue_white.jpg + GT: [dark blue] + VLM: [navy blue] (2 jersey(s), 7.8s) + PASS similar:1 + +[119/161] 119 - black_yellow.jpg + GT: [black, yellow] + VLM: [black, yellow] (3 jersey(s), 10.9s) + PASS exact:2 + +[120/161] 120 - red_dark blue.jpg + GT: [red, dark blue] + VLM: [navy blue, red] (3 jersey(s), 11.1s) + PASS exact:1, similar:1 + +[121/161] 121 - orange_white.jpg + GT: [orange] + VLM: [orange] (3 jersey(s), 10.9s) + PASS exact:1 + +[122/161] 122 - gray.jpg + GT: [gray] + VLM: [gray] (1 jersey(s), 6.3s) + PASS exact:1 + +[123/161] 123 - teal_white.jpg + GT: [teal] + VLM: [teal] (4 jersey(s), 14.1s) + PASS exact:1 + +[124/161] 124 - dark blue_white.jpg + GT: [dark blue] + VLM: [dark blue] (4 jersey(s), 13.9s) + PASS exact:1 + +[125/161] 125 - dark blue_maroon.jpg + GT: [dark blue, maroon] + VLM: [dark blue, red] (2 jersey(s), 8.2s) + PARTIAL exact:1, MISS:maroon, extra:red + +[126/161] 126 - white_blue.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 11.0s) + PASS exact:1 + +[127/161] 127 - yellow.jpg + GT: [yellow] + VLM: [yellow] (4 jersey(s), 13.9s) + PASS exact:1 + +[128/161] 128 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 8.0s) + PASS exact:1 + +[129/161] 129 - blue_white.jpg + GT: [blue] + VLM: [blue] (5 jersey(s), 17.2s) + PASS exact:1 + +[130/161] 130 - yellow_black.jpg + GT: [yellow, black] + VLM: [black, yellow] (2 jersey(s), 8.4s) + PASS exact:2 + +[131/161] 131 - purple_orange.jpg + GT: [purple, orange] + VLM: [orange, purple] (3 jersey(s), 10.8s) + PASS exact:2 + +[132/161] 132 - brown_white.jpg + GT: [brown] + VLM: [orange] (3 jersey(s), 10.8s) + FAIL MISS:brown, extra:orange + +[133/161] 133 - light blue.png + GT: [light blue] + VLM: [light blue] (6 jersey(s), 21.2s) + PASS exact:1 + +[134/161] 134 - teal_white.jpg + GT: [teal] + VLM: [light blue] (1 jersey(s), 5.1s) + FAIL MISS:teal, extra:light blue + +[135/161] 135 - green.jpg + GT: [green] + VLM: [green] (2 jersey(s), 8.1s) + PASS exact:1 + +[136/161] 136 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 8.0s) + PASS exact:1 + +[137/161] 137 - green_white.jpg + GT: [green] + VLM: [green] (3 jersey(s), 11.0s) + PASS exact:1 + +[138/161] 138 - maroon.jpg + GT: [maroon] + VLM: [red] (1 jersey(s), 4.9s) + FAIL MISS:maroon, extra:red + +[139/161] 139 - dark blue_white.jpg + GT: [dark blue] + VLM: [navy blue] (2 jersey(s), 8.3s) + PASS similar:1 + +[140/161] 140 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 7.7s) + PASS exact:1 + +[141/161] 141 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (3 jersey(s), 11.2s) + PASS exact:1 + +[142/161] 142 - orange_white.jpg + GT: [orange] + VLM: [maroon] (2 jersey(s), 8.2s) + FAIL MISS:orange, extra:maroon + +[143/161] 143 - blue_white.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 11.1s) + PASS exact:1 + +[144/161] 144 - green.jpg + GT: [green] + VLM: [green] (10 jersey(s), 31.9s) + PASS exact:1 + +[145/161] 145 - green_white.jpg + GT: [green] + VLM: [(none)] (1 jersey(s), 5.0s) + FAIL MISS:green + +[146/161] 146 - red_gray.jpg + GT: [red, gray] + VLM: [gray, red] (2 jersey(s), 8.0s) + PASS exact:2 + +[147/161] 147 - green.jpg + GT: [green] + VLM: [green] (3 jersey(s), 10.8s) + PASS exact:1 + +[148/161] 148 - yellow_purple.jpg + GT: [yellow, purple] + VLM: [purple, yellow] (2 jersey(s), 7.8s) + PASS exact:2 + +[149/161] 149 - blue_white.jpg + GT: [blue] + VLM: [blue] (5 jersey(s), 16.7s) + PASS exact:1 + +[150/161] 150 - green_gray.jpg + GT: [green, gray] + VLM: [dark blue] (2 jersey(s), 7.9s) + FAIL MISS:green,gray, extra:dark blue + +[151/161] 151 - yellow_black.jpg + GT: [yellow, black] + VLM: [dark blue, yellow] (5 jersey(s), 17.1s) + PARTIAL exact:1, MISS:black, extra:dark blue + +[152/161] 152 - pink_dark blue.jpg + GT: [pink, dark blue] + VLM: [navy blue, pink] (2 jersey(s), 8.3s) + PASS exact:1, similar:1 + +[153/161] 153 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 8.1s) + PASS exact:1 + +[154/161] 154 - dark brown.jpeg + GT: [dark brown] + VLM: [dark brown] (5 jersey(s), 17.3s) + PASS exact:1 + +[155/161] 155 - white_green_gray_purple_yellow.jpg + GT: [green, gray, purple, yellow] + VLM: [gray, purple, yellow] (5 jersey(s), 17.4s) + PARTIAL exact:3, MISS:green + +[156/161] 156 - maroon_gray.jpg + GT: [maroon, gray] + VLM: [maroon] (2 jersey(s), 7.7s) + PARTIAL exact:1, MISS:gray + +[157/161] 157 - blue_white.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 10.7s) + PASS exact:1 + +[158/161] 158 - dark blue_yellow.jpg + GT: [dark blue, yellow] + VLM: [dark blue, yellow] (4 jersey(s), 14.3s) + PASS exact:2 + +[159/161] 159 - blue_white.jpg + GT: [blue] + VLM: [blue] (4 jersey(s), 13.9s) + PASS exact:1 + +[160/161] 160 - blue_white.jpg + GT: [blue] + VLM: [blue] (2 jersey(s), 7.9s) + PASS exact:1 + +[161/161] 161 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 7.9s) + PASS exact:1 + +================================================================================ +ACCURACY SUMMARY +================================================================================ +Images processed: 161 +Errors: 0 +Total time: 1596.1s (9.9s avg) + +Ground truth colors: 202 (excluding white) +VLM unique colors: 185 (excluding white) + +--- Recall (did VLM find each ground truth color?) --- + Exact match: 145 / 202 (71.8%) + Similar match: 22 / 202 (10.9%) + Total found: 167 / 202 (82.7%) + Missed: 35 / 202 (17.3%) + +--- Precision (are VLM colors correct?) --- + Exact match: 145 / 185 (78.4%) + Similar match: 22 / 185 (11.9%) + Total correct: 167 / 185 (90.3%) + Extra/wrong: 18 / 185 (9.7%) + +--- Similar-Match Confusions (expected -> got) --- + navy blue -> blue x6 + gold -> yellow x5 + dark blue -> navy blue x5 + navy blue -> dark blue x1 + brown -> dark brown x1 + navy -> dark blue x1 + blue -> navy blue x1 + green -> dark green x1 + yellow -> gold x1 + +--- Most Missed Ground Truth Colors --- + gray 8 ######## + black 6 ###### + brown 4 #### + green 4 #### + maroon 3 ### + dark brown 2 ## + red 2 ## + teal 2 ## + blue 1 # + light blue 1 # + gold|yellow 1 # + orange 1 # + +--- Most Common Extra/Wrong VLM Colors --- + maroon 5 ##### + black 3 ### + light blue 2 ## + red 2 ## + dark blue 2 ## + gold 1 # + blue 1 # + green 1 # + orange 1 # + +--- Per-Image Verdict --- + PASS 127 + PARTIAL 15 + FAIL 19 + +--- Failed Images (19) --- + 001 -brown_white or dark brown.jpg + missed: brown, dark brown + extra: black + 007 - brown_white.jpg + missed: brown + extra: maroon + 016 - maroon.jpg + missed: maroon + 031 - brown_white.jpg + missed: brown + extra: maroon + 034 - light blue.jpg + missed: light blue + extra: blue + 046 - green.jpg + missed: green + extra: black + 048 - red.jpg + missed: red + extra: maroon + 053 - black_white.jpg + missed: black + 057 - white_gold or yellow.jpg + missed: gold|yellow + 069 - red_white.jpg + missed: red + 077 - teal_white.jpg + missed: teal + extra: green + 083 - dark brown_white.jpg + missed: dark brown + extra: black + 097 - gray_black.jpg + missed: gray, black + extra: light blue + 132 - brown_white.jpg + missed: brown + extra: orange + 134 - teal_white.jpg + missed: teal + extra: light blue + 138 - maroon.jpg + missed: maroon + extra: red + 142 - orange_white.jpg + missed: orange + extra: maroon + 145 - green_white.jpg + missed: green + 150 - green_gray.jpg + missed: green, gray + extra: dark blue + +======================================== +Gemini 3 Flash + jersey_prompt_constrained.txt +Started: Tue Mar 3 06:05:53 PM MST 2026 +======================================== +Model: gemini-3-flash-preview +Images to process: 161 +Concurrency: 8 workers +Prompt: /home/rmcewen/data/dev.python/jersey_test/jersey_prompt_constrained.txt (2223 chars) +================================================================================ +Pre-encoding images ... 161 images in 1.7s +Sending API requests ... + 1/161 API calls completed 2/161 API calls completed 3/161 API calls completed 4/161 API calls completed 5/161 API calls completed 6/161 API calls completed 7/161 API calls completed 8/161 API calls completed 9/161 API calls completed 10/161 API calls completed 11/161 API calls completed 12/161 API calls completed 13/161 API calls completed 14/161 API calls completed 15/161 API calls completed 16/161 API calls completed 17/161 API calls completed 18/161 API calls completed 19/161 API calls completed 20/161 API calls completed 21/161 API calls completed 22/161 API calls completed 23/161 API calls completed 24/161 API calls completed 25/161 API calls completed 26/161 API calls completed 27/161 API calls completed 28/161 API calls completed 29/161 API calls completed 30/161 API calls completed 31/161 API calls completed 32/161 API calls completed 33/161 API calls completed 34/161 API calls completed 35/161 API calls completed 36/161 API calls completed 37/161 API calls completed 38/161 API calls completed 39/161 API calls completed 40/161 API calls completed 41/161 API calls completed 42/161 API calls completed 43/161 API calls completed 44/161 API calls completed 45/161 API calls completed 46/161 API calls completed 47/161 API calls completed 48/161 API calls completed 49/161 API calls completed 50/161 API calls completed 51/161 API calls completed 52/161 API calls completed 53/161 API calls completed 54/161 API calls completed 55/161 API calls completed 56/161 API calls completed 57/161 API calls completed 58/161 API calls completed 59/161 API calls completed 60/161 API calls completed 61/161 API calls completed 62/161 API calls completed 63/161 API calls completed 64/161 API calls completed 65/161 API calls completed 66/161 API calls completed 67/161 API calls completed 68/161 API calls completed 69/161 API calls completed 70/161 API calls completed 71/161 API calls completed 72/161 API calls completed 73/161 API calls completed 74/161 API calls completed 75/161 API calls completed 76/161 API calls completed 77/161 API calls completed 78/161 API calls completed 79/161 API calls completed 80/161 API calls completed 81/161 API calls completed 82/161 API calls completed 83/161 API calls completed 84/161 API calls completed 85/161 API calls completed 86/161 API calls completed 87/161 API calls completed 88/161 API calls completed 89/161 API calls completed 90/161 API calls completed 91/161 API calls completed 92/161 API calls completed 93/161 API calls completed 94/161 API calls completed 95/161 API calls completed 96/161 API calls completed 97/161 API calls completed 98/161 API calls completed 99/161 API calls completed 100/161 API calls completed 101/161 API calls completed 102/161 API calls completed 103/161 API calls completed 104/161 API calls completed 105/161 API calls completed 106/161 API calls completed 107/161 API calls completed 108/161 API calls completed 109/161 API calls completed 110/161 API calls completed 111/161 API calls completed 112/161 API calls completed 113/161 API calls completed 114/161 API calls completed 115/161 API calls completed 116/161 API calls completed 117/161 API calls completed 118/161 API calls completed 119/161 API calls completed 120/161 API calls completed 121/161 API calls completed 122/161 API calls completed 123/161 API calls completed 124/161 API calls completed 125/161 API calls completed 126/161 API calls completed 127/161 API calls completed 128/161 API calls completed 129/161 API calls completed 130/161 API calls completed 131/161 API calls completed 132/161 API calls completed 133/161 API calls completed 134/161 API calls completed 135/161 API calls completed 136/161 API calls completed 137/161 API calls completed 138/161 API calls completed 139/161 API calls completed 140/161 API calls completed 141/161 API calls completed 142/161 API calls completed 143/161 API calls completed 144/161 API calls completed 145/161 API calls completed 146/161 API calls completed 147/161 API calls completed 148/161 API calls completed 149/161 API calls completed 150/161 API calls completed 151/161 API calls completed 152/161 API calls completed 153/161 API calls completed 154/161 API calls completed 155/161 API calls completed 156/161 API calls completed 157/161 API calls completed 158/161 API calls completed 159/161 API calls completed 160/161 API calls completed 161/161 API calls completed (344.4s total) +================================================================================ + +[1/161] 001 -brown_white or dark brown.jpg + GT: [brown, dark brown] + VLM: [dark brown] (2 jersey(s), 36.3s) + PASS exact:1, similar:1 + +[2/161] 002 - yellow.jpg + GT: [yellow] + VLM: [yellow] (2 jersey(s), 6.3s) + PASS exact:1 + +[3/161] 003 - dark blue.jpg + GT: [dark blue] + VLM: [navy blue] (2 jersey(s), 7.5s) + PASS similar:1 + +[4/161] 004 - purple_light blue.jpg + GT: [purple, light blue] + VLM: [light blue, purple] (2 jersey(s), 37.3s) + PASS exact:2 + +[5/161] 005 - white or gray_purple.jpg + GT: [gray, purple] + VLM: [purple] (1 jersey(s), 4.5s) + PARTIAL exact:1, MISS:gray + +[6/161] 006 - navy blue.jpg + GT: [navy blue] + VLM: [navy blue] (1 jersey(s), 5.0s) + PASS exact:1 + +[7/161] 007 - brown_white.jpg + GT: [brown] + VLM: [brown] (2 jersey(s), 6.1s) + PASS exact:1 + +[8/161] 008 -red or orange.jpg + GT: [red|orange] + VLM: [red] (1 jersey(s), 3.2s) + PASS exact:1 + +[9/161] 009 - white_red.jpg + GT: [red] + VLM: [red] (4 jersey(s), 35.1s) + PASS exact:1 + +[10/161] 010 - white_black.jpg + GT: [black] + VLM: [black] (3 jersey(s), 10.5s) + PASS exact:1 + +[11/161] 011 - white or gray_purple.jpg + GT: [gray, purple] + VLM: [purple] (4 jersey(s), 40.8s) + PARTIAL exact:1, MISS:gray + +[12/161] 012 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 5.3s) + PASS exact:1 + +[13/161] 013 - light blue.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 8.9s) + PASS exact:1 + +[14/161] 014 - orange_dark blue or purple.jpg + GT: [orange, dark blue|purple] + VLM: [orange, purple] (3 jersey(s), 9.8s) + PASS exact:2 + +[15/161] 015 - green.jpg + GT: [green] + VLM: [green] (2 jersey(s), 4.4s) + PASS exact:1 + +[16/161] 016 - maroon.jpg + GT: [maroon] + VLM: [(none)] (0 jersey(s), 3.9s) + FAIL MISS:maroon + +[17/161] 017 - brown_white.jpg + GT: [brown] + VLM: [dark brown] (2 jersey(s), 6.5s) + PASS similar:1 + +[18/161] 018 - gray_red.jpg + GT: [gray, red] + VLM: [gray] (1 jersey(s), 8.7s) + PARTIAL exact:1, MISS:red + +[19/161] 019 - maroon_gold.jpg + GT: [maroon, gold] + VLM: [maroon] (1 jersey(s), 4.5s) + PARTIAL exact:1, MISS:gold + +[20/161] 020 - white_brown or orange.jpg + GT: [brown|orange] + VLM: [orange] (2 jersey(s), 4.9s) + PASS exact:1 + +[21/161] 021 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 9.1s) + PASS exact:1 + +[22/161] 022 - black_light blue.jpg + GT: [black, light blue] + VLM: [light blue] (1 jersey(s), 5.0s) + PARTIAL exact:1, MISS:black + +[23/161] 023 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 5.2s) + PASS exact:1 + +[24/161] 024 - white_pink.jpg + GT: [pink] + VLM: [pink] (2 jersey(s), 5.7s) + PASS exact:1 + +[25/161] 025 - blue_green.jpg + GT: [blue, green] + VLM: [green] (1 jersey(s), 3.8s) + PARTIAL exact:1, MISS:blue + +[26/161] 026 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 6.8s) + PASS exact:1 + +[27/161] 027 - red_white.jpg + GT: [red] + VLM: [red] (4 jersey(s), 37.7s) + PASS exact:1 + +[28/161] 028 - green_white.jpg + GT: [green] + VLM: [green] (6 jersey(s), 41.4s) + PASS exact:1 + +[29/161] 029 -maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 7.1s) + PASS exact:1 + +[30/161] 030 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (2 jersey(s), 5.8s) + PASS similar:1 + +[31/161] 031 - brown_white.jpg + GT: [brown] + VLM: [brown] (2 jersey(s), 6.0s) + PASS exact:1 + +[32/161] 032 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 5.9s) + PASS exact:1 + +[33/161] 033 - navy blue_white or gray.jpg + GT: [navy blue, gray] + VLM: [blue] (8 jersey(s), 43.6s) + PARTIAL similar:1, MISS:gray + +[34/161] 034 - light blue.jpg + GT: [light blue] + VLM: [blue] (1 jersey(s), 11.5s) + FAIL MISS:light blue, extra:blue + +[35/161] 035 -green_gold or yellow.jpg + GT: [green, gold|yellow] + VLM: [green] (1 jersey(s), 11.6s) + PARTIAL exact:1, MISS:gold|yellow + +[36/161] 036 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (4 jersey(s), 9.7s) + PASS exact:1 + +[37/161] 037 -navy_white.jpg + GT: [navy] + VLM: [navy blue] (3 jersey(s), 16.0s) + PASS similar:1 + +[38/161] 038 - red_white.jpg + GT: [red] + VLM: [red] (3 jersey(s), 38.7s) + PASS exact:1 + +[39/161] 039 - gray_white.jpg + GT: [gray] + VLM: [gray] (3 jersey(s), 18.4s) + PASS exact:1 + +[40/161] 040 - maroon_gray.jpg + GT: [maroon, gray] + VLM: [gray, maroon] (2 jersey(s), 5.4s) + PASS exact:2 + +[41/161] 041 - navy blue_white.jpg + GT: [navy blue] + VLM: [navy blue] (8 jersey(s), 41.5s) + PASS exact:1 + +[42/161] 042 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 5.1s) + PASS exact:1 + +[43/161] 043 - gray_black.jpg + GT: [gray, black] + VLM: [black, gray] (5 jersey(s), 39.3s) + PASS exact:2 + +[44/161] 044 - purple_black.jpg + GT: [purple, black] + VLM: [purple] (8 jersey(s), 36.4s) + PARTIAL exact:1, MISS:black + +[45/161] 045 - purple.jpg + GT: [purple] + VLM: [purple] (3 jersey(s), 36.0s) + PASS exact:1 + +[46/161] 046 - green.jpg + GT: [green] + VLM: [black] (8 jersey(s), 35.2s) + FAIL MISS:green, extra:black + +[47/161] 047 - purple_white.jpg + GT: [purple] + VLM: [purple] (3 jersey(s), 5.3s) + PASS exact:1 + +[48/161] 048 - red.jpg + GT: [red] + VLM: [(none)] (0 jersey(s), 36.0s) + FAIL MISS:red + +[49/161] 049 - white_gold.jpg + GT: [gold] + VLM: [yellow] (2 jersey(s), 3.6s) + PASS similar:1 + +[50/161] 050 - white_orange.jpg + GT: [orange] + VLM: [orange] (6 jersey(s), 40.4s) + PASS exact:1 + +[51/161] 051 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 5.8s) + PASS exact:1 + +[52/161] 052 - black_gold.jpg + GT: [black, gold] + VLM: [black] (1 jersey(s), 24.0s) + PARTIAL exact:1, MISS:gold + +[53/161] 053 - black_white.jpg + GT: [black] + VLM: [(none)] (1 jersey(s), 4.3s) + FAIL MISS:black + +[54/161] 054 - white_blue.jpg + GT: [blue] + VLM: [blue] (2 jersey(s), 6.5s) + PASS exact:1 + +[55/161] 055 - green_gold.jpg + GT: [green, gold] + VLM: [green, yellow] (2 jersey(s), 12.6s) + PASS exact:1, similar:1 + +[56/161] 056 - white_red.jpg + GT: [red] + VLM: [red] (4 jersey(s), 36.0s) + PASS exact:1 + +[57/161] 057 - white_gold or yellow.jpg + GT: [gold|yellow] + VLM: [(none)] (1 jersey(s), 4.4s) + FAIL MISS:gold|yellow + +[58/161] 058 - purple.jpg + GT: [purple] + VLM: [purple] (4 jersey(s), 6.2s) + PASS exact:1 + +[59/161] 059 - black_gold.jpg + GT: [black, gold] + VLM: [gold] (1 jersey(s), 4.5s) + PARTIAL exact:1, MISS:black + +[60/161] 060 - gray_navy blue.jpg + GT: [gray, navy blue] + VLM: [blue] (2 jersey(s), 7.1s) + PARTIAL similar:1, MISS:gray + +[61/161] 061 - brown or orange.jpg + GT: [brown|orange] + VLM: [orange] (1 jersey(s), 3.4s) + PASS exact:1 + +[62/161] 062 - orange_blue.jpg + GT: [orange, blue] + VLM: [blue, orange] (2 jersey(s), 4.8s) + PASS exact:2 + +[63/161] 063 - dark brown.jpg + GT: [dark brown] + VLM: [brown] (1 jersey(s), 4.7s) + PASS similar:1 + +[64/161] 064 - green_white.jpg + GT: [green] + VLM: [green] (1 jersey(s), 5.3s) + PASS exact:1 + +[65/161] 065 - green_gold.jpg + GT: [green, gold] + VLM: [green, yellow] (5 jersey(s), 37.1s) + PASS exact:1, similar:1 + +[66/161] 066 - yellow.jpg + GT: [yellow] + VLM: [yellow] (1 jersey(s), 6.6s) + PASS exact:1 + +[67/161] 067 - red_white.jpg + GT: [red] + VLM: [red] (5 jersey(s), 36.5s) + PASS exact:1 + +[68/161] 068 - gold.jpg + GT: [gold] + VLM: [gold] (1 jersey(s), 39.5s) + PASS exact:1 + +[69/161] 069 - red_white.jpg + GT: [red] + VLM: [(none)] (5 jersey(s), 40.6s) + FAIL MISS:red + +[70/161] 070 - green_white.jpg + GT: [green] + VLM: [green] (3 jersey(s), 7.9s) + PASS exact:1 + +[71/161] 071 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 4.4s) + PASS exact:1 + +[72/161] 072 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 5.6s) + PASS exact:1 + +[73/161] 073 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (1 jersey(s), 4.2s) + PASS exact:1 + +[74/161] 074 - white_orange.jpg + GT: [orange] + VLM: [(none)] (1 jersey(s), 8.9s) + FAIL MISS:orange + +[75/161] 075 - green_white.jpg + GT: [green] + VLM: [green] (1 jersey(s), 5.0s) + PASS exact:1 + +[76/161] 076 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (4 jersey(s), 38.6s) + PASS exact:1 + +[77/161] 077 - teal_white.jpg + GT: [teal] + VLM: [green] (5 jersey(s), 34.5s) + FAIL MISS:teal, extra:green + +[78/161] 078 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 5.7s) + PASS exact:1 + +[79/161] 079 - blue_maroon.jpg + GT: [blue, maroon] + VLM: [blue, maroon] (6 jersey(s), 10.0s) + PASS exact:2 + +[80/161] 080 - navy blue_white.jpg + GT: [navy blue] + VLM: [blue] (1 jersey(s), 7.9s) + PASS similar:1 + +[81/161] 081 - navy blue.jpg + GT: [navy blue] + VLM: [light blue] (2 jersey(s), 6.6s) + FAIL MISS:navy blue, extra:light blue + +[82/161] 082 - dark blue_white.jpg + GT: [dark blue] + VLM: [navy blue] (3 jersey(s), 21.3s) + PASS similar:1 + +[83/161] 083 - dark brown_white.jpg + GT: [dark brown] + VLM: [dark brown] (2 jersey(s), 40.1s) + PASS exact:1 + +[84/161] 084 - dark brown_yellow.jpg + GT: [dark brown, yellow] + VLM: [dark brown, gold] (2 jersey(s), 8.6s) + PASS exact:1, similar:1 + +[85/161] 085 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 25.5s) + PASS exact:1 + +[86/161] 086 - dark brown_white.jpg + GT: [dark brown] + VLM: [dark brown] (1 jersey(s), 38.5s) + PASS exact:1 + +[87/161] 087 - white_light blue.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 10.2s) + PASS exact:1 + +[88/161] 088 - white_maroon.jpg + GT: [maroon] + VLM: [(none)] (2 jersey(s), 34.9s) + FAIL MISS:maroon + +[89/161] 089 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 7.7s) + PASS exact:1 + +[90/161] 090 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (5 jersey(s), 36.9s) + PASS exact:1 + +[91/161] 091 - teal.jpg + GT: [teal] + VLM: [teal] (3 jersey(s), 7.6s) + PASS exact:1 + +[92/161] 092 - green_white.jpg + GT: [green] + VLM: [green] (6 jersey(s), 40.0s) + PASS exact:1 + +[93/161] 093 - dark blue_white.jpg + GT: [dark blue] + VLM: [navy blue] (2 jersey(s), 6.6s) + PASS similar:1 + +[94/161] 094 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 6.6s) + PASS exact:1 + +[95/161] 095 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 35.6s) + PASS exact:1 + +[96/161] 096 - orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 3.7s) + PASS exact:1 + +[97/161] 097 - gray_black.jpg + GT: [gray, black] + VLM: [gray] (4 jersey(s), 39.1s) + PARTIAL exact:1, MISS:black + +[98/161] 098 - teal_white.jpg + GT: [teal] + VLM: [teal] (2 jersey(s), 35.9s) + PASS exact:1 + +[99/161] 099 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (3 jersey(s), 5.6s) + PASS exact:1 + +[100/161] 100 - orange_white.jpg + GT: [orange] + VLM: [orange] (4 jersey(s), 34.6s) + PASS exact:1 + +[101/161] 101 - green_white.jpg + GT: [green] + VLM: [green] (7 jersey(s), 38.7s) + PASS exact:1 + +[102/161] 102 - yellow-black.jpg + GT: [yellow, black] + VLM: [black] (1 jersey(s), 7.1s) + PARTIAL exact:1, MISS:yellow + +[103/161] 103 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 35.0s) + PASS exact:1 + +[104/161] 104 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 35.3s) + PASS exact:1 + +[105/161] 105 - orange.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 4.8s) + PASS exact:1 + +[106/161] 106 - black_gray.jpg + GT: [black, gray] + VLM: [black, gray] (2 jersey(s), 6.9s) + PASS exact:2 + +[107/161] 107 - orange_white.jpg + GT: [orange] + VLM: [orange] (3 jersey(s), 7.8s) + PASS exact:1 + +[108/161] 108 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 5.3s) + PASS exact:1 + +[109/161] 109 - purple_white.jpg + GT: [purple] + VLM: [purple] (2 jersey(s), 4.8s) + PASS exact:1 + +[110/161] 110 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 7.0s) + PASS exact:1 + +[111/161] 111 - orange_white.jpg + GT: [orange] + VLM: [orange] (2 jersey(s), 10.9s) + PASS exact:1 + +[112/161] 112 - orange_white.jpg + GT: [orange] + VLM: [(none)] (0 jersey(s), 37.6s) + FAIL MISS:orange + +[113/161] 113 - orange.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 3.5s) + PASS exact:1 + +[114/161] 114 - black_white.jpg + GT: [black] + VLM: [black] (2 jersey(s), 5.5s) + PASS exact:1 + +[115/161] 115 - navy blue_maroon.jpg + GT: [navy blue, maroon] + VLM: [blue, maroon] (4 jersey(s), 7.4s) + PASS exact:1, similar:1 + +[116/161] 116 - gray_white.jpg + GT: [gray] + VLM: [gray] (2 jersey(s), 39.7s) + PASS exact:1 + +[117/161] 117 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 37.5s) + PASS exact:1 + +[118/161] 118 - dark blue_white.jpg + GT: [dark blue] + VLM: [navy blue] (2 jersey(s), 12.1s) + PASS similar:1 + +[119/161] 119 - black_yellow.jpg + GT: [black, yellow] + VLM: [black, yellow] (4 jersey(s), 36.4s) + PASS exact:2 + +[120/161] 120 - red_dark blue.jpg + GT: [red, dark blue] + VLM: [navy blue, red] (3 jersey(s), 17.4s) + PASS exact:1, similar:1 + +[121/161] 121 - orange_white.jpg + GT: [orange] + VLM: [orange] (3 jersey(s), 17.7s) + PASS exact:1 + +[122/161] 122 - gray.jpg + GT: [gray] + VLM: [gray] (1 jersey(s), 4.1s) + PASS exact:1 + +[123/161] 123 - teal_white.jpg + GT: [teal] + VLM: [teal] (4 jersey(s), 11.1s) + PASS exact:1 + +[124/161] 124 - dark blue_white.jpg + GT: [dark blue] + VLM: [navy blue] (4 jersey(s), 8.1s) + PASS similar:1 + +[125/161] 125 - dark blue_maroon.jpg + GT: [dark blue, maroon] + VLM: [maroon, navy blue] (4 jersey(s), 17.9s) + PASS exact:1, similar:1 + +[126/161] 126 - white_blue.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 6.8s) + PASS exact:1 + +[127/161] 127 - yellow.jpg + GT: [yellow] + VLM: [black, gold] (5 jersey(s), 39.3s) + PARTIAL similar:1, extra:black + +[128/161] 128 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 11.6s) + PASS exact:1 + +[129/161] 129 - blue_white.jpg + GT: [blue] + VLM: [(none)] (3 jersey(s), 6.1s) + FAIL MISS:blue + +[130/161] 130 - yellow_black.jpg + GT: [yellow, black] + VLM: [yellow] (1 jersey(s), 4.3s) + PARTIAL exact:1, MISS:black + +[131/161] 131 - purple_orange.jpg + GT: [purple, orange] + VLM: [orange, purple] (3 jersey(s), 9.4s) + PASS exact:2 + +[132/161] 132 - brown_white.jpg + GT: [brown] + VLM: [orange] (2 jersey(s), 36.4s) + FAIL MISS:brown, extra:orange + +[133/161] 133 - light blue.png + GT: [light blue] + VLM: [light blue] (7 jersey(s), 38.8s) + PASS exact:1 + +[134/161] 134 - teal_white.jpg + GT: [teal] + VLM: [light blue] (1 jersey(s), 11.2s) + FAIL MISS:teal, extra:light blue + +[135/161] 135 - green.jpg + GT: [green] + VLM: [green] (1 jersey(s), 4.9s) + PASS exact:1 + +[136/161] 136 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 6.8s) + PASS exact:1 + +[137/161] 137 - green_white.jpg + GT: [green] + VLM: [green] (4 jersey(s), 9.8s) + PASS exact:1 + +[138/161] 138 - maroon.jpg + GT: [maroon] + VLM: [red] (1 jersey(s), 4.3s) + FAIL MISS:maroon, extra:red + +[139/161] 139 - dark blue_white.jpg + GT: [dark blue] + VLM: [navy blue] (1 jersey(s), 5.3s) + PASS similar:1 + +[140/161] 140 - red_white.jpg + GT: [red] + VLM: [red] (2 jersey(s), 5.3s) + PASS exact:1 + +[141/161] 141 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (3 jersey(s), 6.3s) + PASS exact:1 + +[142/161] 142 - orange_white.jpg + GT: [orange] + VLM: [orange] (1 jersey(s), 5.3s) + PASS exact:1 + +[143/161] 143 - blue_white.jpg + GT: [blue] + VLM: [blue] (3 jersey(s), 5.7s) + PASS exact:1 + +[144/161] 144 - green.jpg + GT: [green] + VLM: [green] (8 jersey(s), 38.3s) + PASS exact:1 + +[145/161] 145 - green_white.jpg + GT: [green] + VLM: [green] (2 jersey(s), 7.3s) + PASS exact:1 + +[146/161] 146 - red_gray.jpg + GT: [red, gray] + VLM: [gray, red] (2 jersey(s), 4.7s) + PASS exact:2 + +[147/161] 147 - green.jpg + GT: [green] + VLM: [green] (3 jersey(s), 5.2s) + PASS exact:1 + +[148/161] 148 - yellow_purple.jpg + GT: [yellow, purple] + VLM: [purple, yellow] (2 jersey(s), 8.4s) + PASS exact:2 + +[149/161] 149 - blue_white.jpg + GT: [blue] + VLM: [blue] (5 jersey(s), 38.0s) + PASS exact:1 + +[150/161] 150 - green_gray.jpg + GT: [green, gray] + VLM: [black] (2 jersey(s), 10.3s) + FAIL MISS:green,gray, extra:black + +[151/161] 151 - yellow_black.jpg + GT: [yellow, black] + VLM: [gold, navy blue] (6 jersey(s), 35.2s) + PARTIAL similar:1, MISS:black, extra:navy blue + +[152/161] 152 - pink_dark blue.jpg + GT: [pink, dark blue] + VLM: [navy blue, pink] (3 jersey(s), 7.9s) + PASS exact:1, similar:1 + +[153/161] 153 - maroon_white.jpg + GT: [maroon] + VLM: [maroon] (2 jersey(s), 4.6s) + PASS exact:1 + +[154/161] 154 - dark brown.jpeg + GT: [dark brown] + VLM: [brown] (5 jersey(s), 8.9s) + PASS similar:1 + +[155/161] 155 - white_green_gray_purple_yellow.jpg + GT: [green, gray, purple, yellow] + VLM: [gold, gray, purple] (5 jersey(s), 21.6s) + PARTIAL exact:2, similar:1, MISS:green + +[156/161] 156 - maroon_gray.jpg + GT: [maroon, gray] + VLM: [maroon] (2 jersey(s), 15.0s) + PARTIAL exact:1, MISS:gray + +[157/161] 157 - blue_white.jpg + GT: [blue] + VLM: [blue] (5 jersey(s), 37.0s) + PASS exact:1 + +[158/161] 158 - dark blue_yellow.jpg + GT: [dark blue, yellow] + VLM: [gold, navy blue] (5 jersey(s), 37.4s) + PASS similar:2 + +[159/161] 159 - blue_white.jpg + GT: [blue] + VLM: [blue] (5 jersey(s), 10.1s) + PASS exact:1 + +[160/161] 160 - blue_white.jpg + GT: [blue] + VLM: [(none)] (1 jersey(s), 4.3s) + FAIL MISS:blue + +[161/161] 161 - light blue_white.jpg + GT: [light blue] + VLM: [light blue] (2 jersey(s), 4.4s) + PASS exact:1 + +================================================================================ +ACCURACY SUMMARY (gemini-3-flash-preview) +================================================================================ +Images processed: 161 +Errors: 0 +Total time: 344.4s (2.1s avg) + +Ground truth colors: 202 (excluding white) +VLM unique colors: 174 (excluding white) + +--- Recall (did VLM find each ground truth color?) --- + Exact match: 137 / 202 (67.8%) + Similar match: 28 / 202 (13.9%) + Total found: 165 / 202 (81.7%) + Missed: 37 / 202 (18.3%) + +--- Precision (are VLM colors correct?) --- + Exact match: 137 / 174 (78.7%) + Similar match: 27 / 174 (15.5%) + Total correct: 164 / 174 (94.3%) + Extra/wrong: 10 / 174 (5.7%) + +--- Similar-Match Confusions (expected -> got) --- + dark blue -> navy blue x10 + navy blue -> blue x5 + yellow -> gold x5 + gold -> yellow x3 + brown -> dark brown x2 + dark brown -> brown x2 + navy -> navy blue x1 + +--- Most Missed Ground Truth Colors --- + black 7 ####### + gray 6 ###### + maroon 3 ### + red 3 ### + blue 3 ### + green 3 ### + gold 2 ## + gold|yellow 2 ## + orange 2 ## + teal 2 ## + light blue 1 # + navy blue 1 # + yellow 1 # + brown 1 # + +--- Most Common Extra/Wrong VLM Colors --- + black 3 ### + light blue 2 ## + blue 1 # + green 1 # + orange 1 # + red 1 # + navy blue 1 # + +--- Per-Image Verdict --- + PASS 124 + PARTIAL 19 + FAIL 18 + +--- Failed Images (18) --- + 016 - maroon.jpg + missed: maroon + 034 - light blue.jpg + missed: light blue + extra: blue + 046 - green.jpg + missed: green + extra: black + 048 - red.jpg + missed: red + 053 - black_white.jpg + missed: black + 057 - white_gold or yellow.jpg + missed: gold|yellow + 069 - red_white.jpg + missed: red + 074 - white_orange.jpg + missed: orange + 077 - teal_white.jpg + missed: teal + extra: green + 081 - navy blue.jpg + missed: navy blue + extra: light blue + 088 - white_maroon.jpg + missed: maroon + 112 - orange_white.jpg + missed: orange + 129 - blue_white.jpg + missed: blue + 132 - brown_white.jpg + missed: brown + extra: orange + 134 - teal_white.jpg + missed: teal + extra: light blue + 138 - maroon.jpg + missed: maroon + extra: red + 150 - green_gray.jpg + missed: green, gray + extra: black + 160 - blue_white.jpg + missed: blue + +======================================== +All tests completed at: Tue Mar 3 06:11:40 PM MST 2026 diff --git a/jersey_prompt_capstone.txt b/jersey_prompt_capstone.txt new file mode 100644 index 0000000..36698d9 --- /dev/null +++ b/jersey_prompt_capstone.txt @@ -0,0 +1,15 @@ +You are a high-precision sports telemetry system. Your job is to scan the image and output structured data for every visible jersey number. + +**Goal:** Identify every clearly readable jersey number, along with its jersey color and number color. + +**Input Analysis Guidelines:** + +1. **Scan Targets:** Focus entirely on the torso/chest, back, and leg areas of players. +2. **Verify Readability:** For each potential number, check: - Are all digits clearly visible? - Is any part of the number occluded by a limb, fold, or object? - Is the number blurry or too small to read with certainty? - If a number is partially hidden (e.g., looking like a 1 but could be a 7), DISCARD IT. +3. Determine jersey_color from that player's TORSO SHIRT region: - Use the largest contiguous fabric area on the torso (exclude the number itself, stripes/logos, and deep shadows). - Ignore shorts color even if shorts dominate the image. - Choose the single color name that best matches the shirt's base color. + +**Examples:** [Image: Player in red shirt with white '10'] -> {"jerseys": [{"jersey_number": "10", "jersey_color": "red", "number_color": "white"}]} + +**Output Format:** Provide your output in valid JSON format with the following structure. Do not include markdown formatting (like ```json). { "jerseys": [ { "jersey_number": , "jersey_color": , "number_color": } ] } + +**Constraint:** - If no numbers are clearly readable, return "jerseys": []. - Do not guess. Precision is more important than recall. \ No newline at end of file diff --git a/jersey_prompt_constrained.txt b/jersey_prompt_constrained.txt new file mode 100644 index 0000000..7f7a54e --- /dev/null +++ b/jersey_prompt_constrained.txt @@ -0,0 +1,56 @@ +You are an expert at detecting sports jerseys in images. Carefully examine the provided image and identify all visible sports jerseys. + +CRITICAL INSTRUCTIONS: +1. ONLY detect jerseys that are CLEARLY VISIBLE in the image +2. ONLY include jersey numbers that you can ACTUALLY READ in the image +3. If you CANNOT see any jerseys, you MUST return {"jerseys": []} +4. DO NOT make up, imagine, or guess jersey numbers that aren't visible +5. DO NOT include jerseys if you cannot clearly see the number + +COLOR VOCABULARY: +For "jersey_color" and "number_color", you MUST choose from this list ONLY: +red, blue, dark blue, navy blue, light blue, green, yellow, gold, orange, purple, black, white, gray, brown, dark brown, maroon, teal, pink + +Important color distinctions: +- Use "maroon" for dark brownish-red, NOT "red" +- Use "light blue" for pale or sky blue, NOT "blue" +- Use "navy blue" for very dark blue, NOT "blue" or "dark blue" +- Use "teal" for blue-green, NOT "green" or "blue" +- Use "gray" (not "grey") for silver or neutral tones +- Use "dark brown" for very dark brown, NOT "black" +- Use "gold" for metallic or deep yellow, NOT "yellow" + +RESPONSE FORMAT: +Respond ONLY with a valid JSON object. No explanations, no markdown, no extra text. + +Use DOUBLE QUOTES (") for all JSON keys and string values. + +The JSON must have a single key "jerseys" with an array of dictionaries. + +Each dictionary must have exactly these three keys: +- "jersey_number": The number on the jersey (as a string, only if clearly visible) +- "jersey_color": The primary color of the jersey (MUST be from the color list above) +- "number_color": The color of the number on the jersey (MUST be from the color list above) + +Example response for an image WITH visible jerseys: +{ + "jerseys": [ + { + "jersey_number": "10", + "jersey_color": "maroon", + "number_color": "gold" + }, + { + "jersey_number": "42", + "jersey_color": "light blue", + "number_color": "white" + } + ] +} + +Example response for an image WITHOUT jerseys or with unclear numbers: +{"jerseys": []} + +REMEMBER: Only include jerseys with numbers you can ACTUALLY SEE in the image. When in doubt, return empty array. + +Now analyze the image and return the JSON object. \ No newline at end of file diff --git a/pyproject.toml b/pyproject.toml new file mode 100644 index 0000000..5da942f --- /dev/null +++ b/pyproject.toml @@ -0,0 +1,11 @@ +[project] +name = "jersey-test" +version = "0.1.0" +description = "Add your description here" +readme = "README.md" +requires-python = ">=3.12" +dependencies = [ + "numpy>=1.24.0", + "opencv-python>=4.8.0", + "requests>=2.28.0", +] diff --git a/run_all_accuracy_tests.sh b/run_all_accuracy_tests.sh new file mode 100755 index 0000000..0e2d097 --- /dev/null +++ b/run_all_accuracy_tests.sh @@ -0,0 +1,44 @@ +#!/usr/bin/env bash +# +# Run both accuracy test scripts against all three prompts. +# Results are saved to accuracy_test_results_all.txt +# + +set -e + +SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)" +OUTPUT_FILE="${SCRIPT_DIR}/accuracy_test_results_all.txt" + +PROMPTS=( + "jersey_prompt.txt" + "jersey_prompt_capstone.txt" + "jersey_prompt_constrained.txt" +) + +echo "Results will be saved to: ${OUTPUT_FILE}" +echo "Started at: $(date)" +echo "" + +> "$OUTPUT_FILE" + +for prompt in "${PROMPTS[@]}"; do + prompt_path="${SCRIPT_DIR}/${prompt}" + + echo "========================================" | tee -a "$OUTPUT_FILE" + echo "Qwen3-VL-8B + ${prompt}" | tee -a "$OUTPUT_FILE" + echo "Started: $(date)" | tee -a "$OUTPUT_FILE" + echo "========================================" | tee -a "$OUTPUT_FILE" + python3 "${SCRIPT_DIR}/test_accuracy.py" "$prompt_path" 2>&1 | tee -a "$OUTPUT_FILE" + echo "" | tee -a "$OUTPUT_FILE" + + echo "========================================" | tee -a "$OUTPUT_FILE" + echo "Gemini 3 Flash + ${prompt}" | tee -a "$OUTPUT_FILE" + echo "Started: $(date)" | tee -a "$OUTPUT_FILE" + echo "========================================" | tee -a "$OUTPUT_FILE" + python3 "${SCRIPT_DIR}/test_accuracy_gemini.py" "$prompt_path" 2>&1 | tee -a "$OUTPUT_FILE" + echo "" | tee -a "$OUTPUT_FILE" +done + +echo "========================================" | tee -a "$OUTPUT_FILE" +echo "All tests completed at: $(date)" | tee -a "$OUTPUT_FILE" +echo "Results saved to: ${OUTPUT_FILE}" diff --git a/test_accuracy.py b/test_accuracy.py new file mode 100644 index 0000000..7747506 --- /dev/null +++ b/test_accuracy.py @@ -0,0 +1,402 @@ +#!/usr/bin/env python3 +""" +Test script to measure VLM accuracy for jersey color detection. + +Uses annotated test images where ground truth colors are encoded in filenames. +Compares VLM results against ground truth, measuring exact and similar color matches. +White is ignored in both ground truth and VLM results. + +Filename format: "014 - orange_dark blue or purple.jpg" + - Underscore separates distinct jersey colors + - "or" separates acceptable alternatives for a single jersey + +Usage: + python test_accuracy.py [prompt_file] +""" + +import json +import os +import re +import sys +import time +from collections import Counter +from pathlib import Path + +import cv2 + +sys.path.insert(0, os.path.dirname(os.path.abspath(__file__))) +from scan_utils.llama_cpp_client import LlamaCppClient + +SERVER_URL = "http://agx:8080" +IMAGES_DIR = os.path.join(os.path.dirname(__file__), "basketball_jersery_color_test_files_annotated") +DEFAULT_PROMPT_FILE = os.path.join(os.path.dirname(__file__), "jersey_prompt.txt") +MAX_IMAGE_WIDTH = 768 + +# --------------------------------------------------------------------------- +# Color similarity – colors in the same family count as "similar" matches +# --------------------------------------------------------------------------- +COLOR_FAMILIES = { + 'blue': ['blue', 'dark blue', 'navy blue', 'navy', 'royal blue'], + 'light_blue': ['light blue', 'sky blue', 'baby blue', 'carolina blue', 'powder blue'], + 'red': ['red', 'scarlet', 'crimson'], + 'dark_red': ['maroon', 'burgundy', 'dark red', 'wine'], + 'green': ['green', 'dark green', 'forest green', 'kelly green'], + 'yellow': ['yellow', 'gold', 'golden'], + 'orange': ['orange', 'burnt orange'], + 'brown': ['brown', 'dark brown'], + 'purple': ['purple', 'violet'], + 'gray': ['gray', 'grey', 'silver', 'charcoal'], + 'black': ['black'], + 'teal': ['teal', 'turquoise', 'cyan', 'aqua'], + 'pink': ['pink', 'magenta', 'hot pink', 'rose'], +} + +_COLOR_TO_FAMILY = {} +for _family, _members in COLOR_FAMILIES.items(): + for _color in _members: + _COLOR_TO_FAMILY[_color] = _family + + +def colors_are_similar(color1: str, color2: str) -> bool: + """Return True if two colors belong to the same color family.""" + if color1 == color2: + return True + f1 = _COLOR_TO_FAMILY.get(color1) + f2 = _COLOR_TO_FAMILY.get(color2) + return bool(f1 and f2 and f1 == f2) + + +# --------------------------------------------------------------------------- +# Ground-truth parsing +# --------------------------------------------------------------------------- +def parse_ground_truth(filename: str) -> list[list[str]]: + """Parse ground truth colors from an annotated filename. + + Returns a list of color groups. Each group is a list of acceptable + alternatives (from "or" in the filename). White entries are removed. + + Example: "014 - orange_dark blue or purple.jpg" + -> [["orange"], ["dark blue", "purple"]] + """ + name = Path(filename).stem + # Strip number prefix ("014 - ", "029 -", etc.) + name = re.sub(r'^\d+\s*-\s*', '', name) + # Treat hyphens between colors as underscores (e.g. "yellow-black") + name = name.replace('-', '_') + + color_groups = [] + for part in name.split('_'): + part = part.strip() + if not part: + continue + alternatives = [a.strip().lower() for a in part.split(' or ')] + alternatives = [a for a in alternatives if a and a != 'white'] + if alternatives: + color_groups.append(alternatives) + return color_groups + + +# --------------------------------------------------------------------------- +# Response cleaning +# --------------------------------------------------------------------------- +def clean_response(text: str) -> str: + """Remove think tags and markdown code blocks from model output.""" + cleaned = re.sub(r'.*?', '', text, flags=re.DOTALL | re.IGNORECASE) + cleaned = re.sub(r'\u25c1think\u25b7.*?\u25c1/think\u25b7', '', cleaned, flags=re.DOTALL) + cleaned = re.sub(r'', '', cleaned, flags=re.IGNORECASE) + cleaned = re.sub(r'\u25c1/?think\u25b7', '', cleaned, flags=re.IGNORECASE) + + json_block = re.search(r'```(?:json)?\s*\n?(.*?)\n?```', cleaned, flags=re.DOTALL | re.IGNORECASE) + if json_block: + cleaned = json_block.group(1) + else: + cleaned = re.sub(r'```(?:json)?', '', cleaned, flags=re.IGNORECASE) + + return cleaned.strip() + + +# --------------------------------------------------------------------------- +# Scoring +# --------------------------------------------------------------------------- +def score_image(gt_groups: list[list[str]], vlm_colors: set[str]) -> dict: + """Compare VLM detected colors against ground truth color groups. + + Recall = how many GT color groups were found in VLM output + Precision = how many VLM colors match something in the GT + """ + recall_exact = 0 + recall_similar = 0 + recall_missed = [] + confusions = [] + + for group in gt_groups: + # Try exact match first + if any(alt in vlm_colors for alt in group): + recall_exact += 1 + continue + # Try similar match + matched_vlm = None + for alt in group: + for vc in vlm_colors: + if colors_are_similar(alt, vc): + matched_vlm = vc + break + if matched_vlm: + break + if matched_vlm: + recall_similar += 1 + confusions.append((group, matched_vlm)) + else: + recall_missed.append(group) + + # Precision: check each VLM color against GT + all_gt_alts = [alt for group in gt_groups for alt in group] + precision_exact = 0 + precision_similar = 0 + precision_extra = [] + for vc in vlm_colors: + if vc in all_gt_alts: + precision_exact += 1 + elif any(colors_are_similar(vc, gt) for gt in all_gt_alts): + precision_similar += 1 + else: + precision_extra.append(vc) + + return { + 'gt_count': len(gt_groups), + 'vlm_count': len(vlm_colors), + 'recall_exact': recall_exact, + 'recall_similar': recall_similar, + 'recall_missed': recall_missed, + 'precision_exact': precision_exact, + 'precision_similar': precision_similar, + 'precision_extra': precision_extra, + 'confusions': confusions, + } + + +# --------------------------------------------------------------------------- +# Helpers +# --------------------------------------------------------------------------- +def pct(n: int, d: int) -> str: + return f"{100 * n / d:.1f}%" if d else "N/A" + + +def print_summary(total_gt, total_vlm, total_recall_exact, total_recall_similar, + total_recall_missed, total_precision_exact, total_precision_similar, + total_precision_extra, confusion_counter, missed_counter, + extra_counter, per_image_results, image_count, errors, total_time): + """Print the full accuracy summary report.""" + print() + print("=" * 80) + print("ACCURACY SUMMARY") + print("=" * 80) + print(f"Images processed: {image_count}") + print(f"Errors: {errors}") + print(f"Total time: {total_time:.1f}s ({total_time / max(image_count, 1):.1f}s avg)") + print() + print(f"Ground truth colors: {total_gt} (excluding white)") + print(f"VLM unique colors: {total_vlm} (excluding white)") + print() + + print("--- Recall (did VLM find each ground truth color?) ---") + print(f" Exact match: {total_recall_exact:4d} / {total_gt} ({pct(total_recall_exact, total_gt)})") + print(f" Similar match: {total_recall_similar:4d} / {total_gt} ({pct(total_recall_similar, total_gt)})") + recall_total = total_recall_exact + total_recall_similar + print(f" Total found: {recall_total:4d} / {total_gt} ({pct(recall_total, total_gt)})") + print(f" Missed: {total_recall_missed:4d} / {total_gt} ({pct(total_recall_missed, total_gt)})") + print() + + print("--- Precision (are VLM colors correct?) ---") + print(f" Exact match: {total_precision_exact:4d} / {total_vlm} ({pct(total_precision_exact, total_vlm)})") + print(f" Similar match: {total_precision_similar:4d} / {total_vlm} ({pct(total_precision_similar, total_vlm)})") + prec_total = total_precision_exact + total_precision_similar + print(f" Total correct: {prec_total:4d} / {total_vlm} ({pct(prec_total, total_vlm)})") + print(f" Extra/wrong: {total_precision_extra:4d} / {total_vlm} ({pct(total_precision_extra, total_vlm)})") + + if confusion_counter: + print() + print("--- Similar-Match Confusions (expected -> got) ---") + for (expected, got), count in confusion_counter.most_common(): + print(f" {expected:30s} -> {got:20s} x{count}") + + if missed_counter: + print() + print("--- Most Missed Ground Truth Colors ---") + for color, count in missed_counter.most_common(20): + bar = "#" * min(count, 40) + print(f" {color:30s} {count:3d} {bar}") + + if extra_counter: + print() + print("--- Most Common Extra/Wrong VLM Colors ---") + for color, count in extra_counter.most_common(20): + bar = "#" * min(count, 40) + print(f" {color:30s} {count:3d} {bar}") + + if per_image_results: + tags = Counter(r['tag'] for r in per_image_results) + print() + print("--- Per-Image Verdict ---") + for tag in ['PASS', 'PARTIAL', 'FAIL']: + print(f" {tag:10s} {tags.get(tag, 0):4d}") + + failed = [r for r in per_image_results if r['tag'] == 'FAIL'] + if failed: + print() + print(f"--- Failed Images ({len(failed)}) ---") + for r in failed: + scores = r['scores'] + missed_strs = ["|".join(g) for g in scores['recall_missed']] + print(f" {r['file']}") + print(f" missed: {', '.join(missed_strs)}") + if scores['precision_extra']: + print(f" extra: {', '.join(scores['precision_extra'])}") + + +# --------------------------------------------------------------------------- +# Main +# --------------------------------------------------------------------------- +def main(): + prompt_file = sys.argv[1] if len(sys.argv) > 1 else DEFAULT_PROMPT_FILE + + with open(prompt_file, 'r') as f: + prompt = f.read() + + valid_extensions = {'.jpg', '.jpeg', '.png', '.bmp', '.tiff', '.webp'} + image_files = sorted([ + p for p in Path(IMAGES_DIR).iterdir() + if p.suffix.lower() in valid_extensions + ]) + + print(f"Images to process: {len(image_files)}") + print(f"Server: {SERVER_URL}") + print(f"Prompt: {prompt_file} ({len(prompt)} chars)") + print("=" * 80) + + client = LlamaCppClient(base_url=SERVER_URL) + + # Accumulators + total_gt = 0 + total_vlm = 0 + total_recall_exact = 0 + total_recall_similar = 0 + total_recall_missed = 0 + total_precision_exact = 0 + total_precision_similar = 0 + total_precision_extra = 0 + errors = 0 + start_all = time.time() + + confusion_counter = Counter() + missed_counter = Counter() + extra_counter = Counter() + per_image_results = [] + + for i, image_path in enumerate(image_files, 1): + gt_groups = parse_ground_truth(image_path.name) + gt_display = ", ".join("|".join(g) for g in gt_groups) if gt_groups else "(none)" + print(f"\n[{i}/{len(image_files)}] {image_path.name}") + print(f" GT: [{gt_display}]") + + image = cv2.imread(str(image_path)) + if image is None: + print(" SKIP (failed to load)") + errors += 1 + continue + + h, w = image.shape[:2] + if w > MAX_IMAGE_WIDTH: + scale = MAX_IMAGE_WIDTH / w + image = cv2.resize(image, (MAX_IMAGE_WIDTH, int(h * scale)), interpolation=cv2.INTER_AREA) + + message = client.create_multimodal_message(role="user", content=prompt, images=[image]) + + try: + t0 = time.time() + response = client.chat_completion(messages=[message], temperature=0.1, max_tokens=1000) + elapsed = time.time() - t0 + + response_text = response['choices'][0]['message']['content'] + cleaned = clean_response(response_text) + result = json.loads(cleaned) + jerseys = result.get('jerseys', []) + + # Unique VLM jersey colors, ignoring white + vlm_colors = set() + for j in jerseys: + jc = j.get('jersey_color', '').strip().lower() + if jc and jc != 'white': + vlm_colors.add(jc) + + vlm_display = ", ".join(sorted(vlm_colors)) if vlm_colors else "(none)" + print(f" VLM: [{vlm_display}] ({len(jerseys)} jersey(s), {elapsed:.1f}s)") + + if not gt_groups: + print(" -- no ground truth colors (white-only), skipping scoring") + continue + + scores = score_image(gt_groups, vlm_colors) + total_gt += scores['gt_count'] + total_vlm += scores['vlm_count'] + total_recall_exact += scores['recall_exact'] + total_recall_similar += scores['recall_similar'] + total_recall_missed += len(scores['recall_missed']) + total_precision_exact += scores['precision_exact'] + total_precision_similar += scores['precision_similar'] + total_precision_extra += len(scores['precision_extra']) + + for group, got in scores['confusions']: + confusion_counter[("|".join(group), got)] += 1 + for group in scores['recall_missed']: + missed_counter["|".join(group)] += 1 + for ec in scores['precision_extra']: + extra_counter[ec] += 1 + + # Status line + status_parts = [] + if scores['recall_exact']: + status_parts.append(f"exact:{scores['recall_exact']}") + if scores['recall_similar']: + status_parts.append(f"similar:{scores['recall_similar']}") + if scores['recall_missed']: + missed_strs = ["|".join(g) for g in scores['recall_missed']] + status_parts.append(f"MISS:{','.join(missed_strs)}") + if scores['precision_extra']: + status_parts.append(f"extra:{','.join(scores['precision_extra'])}") + + all_found = (scores['recall_exact'] + scores['recall_similar']) == scores['gt_count'] + no_extra = not scores['precision_extra'] + if all_found and no_extra: + tag = "PASS" + elif scores['recall_exact'] + scores['recall_similar'] > 0: + tag = "PARTIAL" + else: + tag = "FAIL" + print(f" {tag} {', '.join(status_parts)}") + + per_image_results.append({ + 'file': image_path.name, + 'tag': tag, + 'scores': scores, + }) + + except (json.JSONDecodeError, KeyError, IndexError) as e: + print(f" PARSE ERROR: {e}") + errors += 1 + except Exception as e: + print(f" ERROR: {e}") + errors += 1 + + total_time = time.time() - start_all + + print_summary( + total_gt, total_vlm, total_recall_exact, total_recall_similar, + total_recall_missed, total_precision_exact, total_precision_similar, + total_precision_extra, confusion_counter, missed_counter, + extra_counter, per_image_results, len(image_files), errors, total_time, + ) + + +if __name__ == '__main__': + main() diff --git a/test_accuracy_gemini.py b/test_accuracy_gemini.py new file mode 100644 index 0000000..07cd55c --- /dev/null +++ b/test_accuracy_gemini.py @@ -0,0 +1,576 @@ +#!/usr/bin/env python3 +""" +Test script to measure Gemini VLM accuracy for jersey color detection. + +Uses annotated test images where ground truth colors are encoded in filenames. +Compares Gemini results against ground truth, measuring exact and similar color +matches. White is ignored in both ground truth and VLM results. + +Filename format: "014 - orange_dark blue or purple.jpg" + - Underscore separates distinct jersey colors + - "or" separates acceptable alternatives for a single jersey + +Usage: + python test_accuracy_gemini.py [prompt_file] +""" + +import base64 +import concurrent.futures +import json +import os +import re +import sys +import time +from collections import Counter +from pathlib import Path + +import cv2 +import requests + +GEMINI_MODEL = "gemini-3-flash-preview" +API_URL = f"https://generativelanguage.googleapis.com/v1beta/models/{GEMINI_MODEL}:generateContent" + +IMAGES_DIR = os.path.join(os.path.dirname(__file__), "basketball_jersery_color_test_files_annotated") +DEFAULT_PROMPT_FILE = os.path.join(os.path.dirname(__file__), "jersey_prompt.txt") +API_KEY_FILE = os.path.join(os.path.dirname(__file__), "gemini_api_key.txt") +MAX_IMAGE_WIDTH = 768 +JPEG_QUALITY = 85 +CONCURRENT_WORKERS = 8 + +# --------------------------------------------------------------------------- +# Color similarity – colors in the same family count as "similar" matches +# --------------------------------------------------------------------------- +COLOR_FAMILIES = { + 'blue': ['blue', 'dark blue', 'navy blue', 'navy', 'royal blue'], + 'light_blue': ['light blue', 'sky blue', 'baby blue', 'carolina blue', 'powder blue'], + 'red': ['red', 'scarlet', 'crimson'], + 'dark_red': ['maroon', 'burgundy', 'dark red', 'wine'], + 'green': ['green', 'dark green', 'forest green', 'kelly green'], + 'yellow': ['yellow', 'gold', 'golden'], + 'orange': ['orange', 'burnt orange'], + 'brown': ['brown', 'dark brown'], + 'purple': ['purple', 'violet'], + 'gray': ['gray', 'grey', 'silver', 'charcoal'], + 'black': ['black'], + 'teal': ['teal', 'turquoise', 'cyan', 'aqua'], + 'pink': ['pink', 'magenta', 'hot pink', 'rose'], +} + +_COLOR_TO_FAMILY = {} +for _family, _members in COLOR_FAMILIES.items(): + for _color in _members: + _COLOR_TO_FAMILY[_color] = _family + + +def colors_are_similar(color1: str, color2: str) -> bool: + """Return True if two colors belong to the same color family.""" + if color1 == color2: + return True + f1 = _COLOR_TO_FAMILY.get(color1) + f2 = _COLOR_TO_FAMILY.get(color2) + return bool(f1 and f2 and f1 == f2) + + +# --------------------------------------------------------------------------- +# Ground-truth parsing +# --------------------------------------------------------------------------- +def parse_ground_truth(filename: str) -> list[list[str]]: + """Parse ground truth colors from an annotated filename. + + Returns a list of color groups. Each group is a list of acceptable + alternatives (from "or" in the filename). White entries are removed. + + Example: "014 - orange_dark blue or purple.jpg" + -> [["orange"], ["dark blue", "purple"]] + """ + name = Path(filename).stem + # Strip number prefix ("014 - ", "029 -", etc.) + name = re.sub(r'^\d+\s*-\s*', '', name) + # Treat hyphens between colors as underscores (e.g. "yellow-black") + name = name.replace('-', '_') + + color_groups = [] + for part in name.split('_'): + part = part.strip() + if not part: + continue + alternatives = [a.strip().lower() for a in part.split(' or ')] + alternatives = [a for a in alternatives if a and a != 'white'] + if alternatives: + color_groups.append(alternatives) + return color_groups + + +# --------------------------------------------------------------------------- +# Response cleaning & salvage +# --------------------------------------------------------------------------- +def clean_response(text: str) -> str: + """Remove think tags and markdown code blocks from model output.""" + cleaned = re.sub(r'.*?', '', text, flags=re.DOTALL | re.IGNORECASE) + cleaned = re.sub(r'', '', cleaned, flags=re.IGNORECASE) + + json_block = re.search(r'```(?:json)?\s*\n?(.*?)\n?```', cleaned, flags=re.DOTALL | re.IGNORECASE) + if json_block: + cleaned = json_block.group(1) + else: + cleaned = re.sub(r'```(?:json)?', '', cleaned, flags=re.IGNORECASE) + + return cleaned.strip() + + +def salvage_jerseys(text: str) -> list[dict]: + """Extract complete jersey objects from truncated JSON using regex.""" + pattern = re.compile( + r'\{\s*' + r'"jersey_number"\s*:\s*"[^"]*"\s*,\s*' + r'"jersey_color"\s*:\s*"([^"]*)"\s*,\s*' + r'"number_color"\s*:\s*"([^"]*)"\s*' + r'\}', + re.DOTALL, + ) + jerseys = [] + for m in pattern.finditer(text): + jerseys.append({ + 'jersey_color': m.group(1), + 'number_color': m.group(2), + }) + return jerseys + + +# --------------------------------------------------------------------------- +# Gemini API helpers +# --------------------------------------------------------------------------- +def load_api_key() -> str: + with open(API_KEY_FILE, 'r') as f: + return f.read().strip() + + +def encode_image(image_path: str) -> tuple[str, str]: + """Read an image file, resize if wider than MAX_IMAGE_WIDTH, and return (base64_data, mime_type).""" + ext = Path(image_path).suffix.lower() + mime_map = { + '.jpg': 'image/jpeg', + '.jpeg': 'image/jpeg', + '.png': 'image/png', + '.webp': 'image/webp', + '.bmp': 'image/bmp', + '.tiff': 'image/tiff', + } + mime_type = mime_map.get(ext, 'image/jpeg') + + image = cv2.imread(image_path) + if image is not None: + h, w = image.shape[:2] + if w > MAX_IMAGE_WIDTH: + scale = MAX_IMAGE_WIDTH / w + image = cv2.resize(image, (MAX_IMAGE_WIDTH, int(h * scale)), interpolation=cv2.INTER_AREA) + if ext == '.png': + _, buf = cv2.imencode('.png', image) + else: + _, buf = cv2.imencode('.jpg', image, [cv2.IMWRITE_JPEG_QUALITY, JPEG_QUALITY]) + data = base64.b64encode(buf).decode('utf-8') + else: + with open(image_path, 'rb') as f: + data = base64.b64encode(f.read()).decode('utf-8') + + return data, mime_type + + +MAX_RETRIES = 3 +RETRY_BACKOFF = [2, 5, 10] + + +def call_gemini(session: requests.Session, api_key: str, image_data: str, + mime_type: str, prompt: str) -> dict: + """Send pre-encoded image + prompt to the Gemini API and return the raw response.""" + payload = { + "contents": [{ + "parts": [ + { + "inline_data": { + "mime_type": mime_type, + "data": image_data, + } + }, + { + "text": prompt, + } + ] + }], + "generationConfig": { + "temperature": 0.1, + "maxOutputTokens": 8192, + "responseMimeType": "application/json", + } + } + + for attempt in range(MAX_RETRIES): + response = session.post( + API_URL, + headers={ + "x-goog-api-key": api_key, + "Content-Type": "application/json", + }, + json=payload, + ) + + if response.status_code >= 500 and attempt < MAX_RETRIES - 1: + time.sleep(RETRY_BACKOFF[attempt]) + continue + + response.raise_for_status() + return response.json() + + response.raise_for_status() + return response.json() + + +def _api_worker(session: requests.Session, api_key: str, image_data: str, + mime_type: str, prompt: str) -> dict: + """Wrapper that captures timing and exceptions for concurrent execution.""" + t0 = time.time() + try: + resp = call_gemini(session, api_key, image_data, mime_type, prompt) + return {'resp': resp, 'elapsed': time.time() - t0, 'error': None} + except Exception as e: + return {'resp': None, 'elapsed': time.time() - t0, 'error': e} + + +# --------------------------------------------------------------------------- +# Scoring +# --------------------------------------------------------------------------- +def score_image(gt_groups: list[list[str]], vlm_colors: set[str]) -> dict: + """Compare VLM detected colors against ground truth color groups. + + Recall = how many GT color groups were found in VLM output + Precision = how many VLM colors match something in the GT + """ + recall_exact = 0 + recall_similar = 0 + recall_missed = [] + confusions = [] + + for group in gt_groups: + # Try exact match first + if any(alt in vlm_colors for alt in group): + recall_exact += 1 + continue + # Try similar match + matched_vlm = None + for alt in group: + for vc in vlm_colors: + if colors_are_similar(alt, vc): + matched_vlm = vc + break + if matched_vlm: + break + if matched_vlm: + recall_similar += 1 + confusions.append((group, matched_vlm)) + else: + recall_missed.append(group) + + # Precision: check each VLM color against GT + all_gt_alts = [alt for group in gt_groups for alt in group] + precision_exact = 0 + precision_similar = 0 + precision_extra = [] + for vc in vlm_colors: + if vc in all_gt_alts: + precision_exact += 1 + elif any(colors_are_similar(vc, gt) for gt in all_gt_alts): + precision_similar += 1 + else: + precision_extra.append(vc) + + return { + 'gt_count': len(gt_groups), + 'vlm_count': len(vlm_colors), + 'recall_exact': recall_exact, + 'recall_similar': recall_similar, + 'recall_missed': recall_missed, + 'precision_exact': precision_exact, + 'precision_similar': precision_similar, + 'precision_extra': precision_extra, + 'confusions': confusions, + } + + +# --------------------------------------------------------------------------- +# Helpers +# --------------------------------------------------------------------------- +def pct(n: int, d: int) -> str: + return f"{100 * n / d:.1f}%" if d else "N/A" + + +def extract_vlm_colors(jerseys: list[dict]) -> set[str]: + """Return unique jersey colors from VLM output, ignoring white.""" + vlm_colors = set() + for j in jerseys: + jc = j.get('jersey_color', '').strip().lower() + if jc and jc != 'white': + vlm_colors.add(jc) + return vlm_colors + + +def parse_response(result: dict) -> tuple[list[dict], set[str]]: + """Parse a Gemini response into jerseys list and vlm_colors set. + + On JSON parse failure, attempts to salvage jersey objects from truncated + output. Returns (jerseys, vlm_colors). + """ + text = result['resp']['candidates'][0]['content']['parts'][0]['text'] + cleaned = clean_response(text) + try: + data = json.loads(cleaned) + jerseys = data.get('jerseys', []) + except json.JSONDecodeError: + jerseys = salvage_jerseys(text) + return jerseys, extract_vlm_colors(jerseys) + + +def score_and_format(gt_groups, vlm_colors, scores): + """Build a status line and tag from scoring results.""" + status_parts = [] + if scores['recall_exact']: + status_parts.append(f"exact:{scores['recall_exact']}") + if scores['recall_similar']: + status_parts.append(f"similar:{scores['recall_similar']}") + if scores['recall_missed']: + missed_strs = ["|".join(g) for g in scores['recall_missed']] + status_parts.append(f"MISS:{','.join(missed_strs)}") + if scores['precision_extra']: + status_parts.append(f"extra:{','.join(scores['precision_extra'])}") + + all_found = (scores['recall_exact'] + scores['recall_similar']) == scores['gt_count'] + no_extra = not scores['precision_extra'] + if all_found and no_extra: + tag = "PASS" + elif scores['recall_exact'] + scores['recall_similar'] > 0: + tag = "PARTIAL" + else: + tag = "FAIL" + return tag, status_parts + + +def print_summary(model_name, total_gt, total_vlm, total_recall_exact, + total_recall_similar, total_recall_missed, + total_precision_exact, total_precision_similar, + total_precision_extra, confusion_counter, missed_counter, + extra_counter, per_image_results, image_count, errors, + total_time): + """Print the full accuracy summary report.""" + print() + print("=" * 80) + print(f"ACCURACY SUMMARY ({model_name})") + print("=" * 80) + print(f"Images processed: {image_count}") + print(f"Errors: {errors}") + print(f"Total time: {total_time:.1f}s ({total_time / max(image_count, 1):.1f}s avg)") + print() + print(f"Ground truth colors: {total_gt} (excluding white)") + print(f"VLM unique colors: {total_vlm} (excluding white)") + print() + + print("--- Recall (did VLM find each ground truth color?) ---") + print(f" Exact match: {total_recall_exact:4d} / {total_gt} ({pct(total_recall_exact, total_gt)})") + print(f" Similar match: {total_recall_similar:4d} / {total_gt} ({pct(total_recall_similar, total_gt)})") + recall_total = total_recall_exact + total_recall_similar + print(f" Total found: {recall_total:4d} / {total_gt} ({pct(recall_total, total_gt)})") + print(f" Missed: {total_recall_missed:4d} / {total_gt} ({pct(total_recall_missed, total_gt)})") + print() + + print("--- Precision (are VLM colors correct?) ---") + print(f" Exact match: {total_precision_exact:4d} / {total_vlm} ({pct(total_precision_exact, total_vlm)})") + print(f" Similar match: {total_precision_similar:4d} / {total_vlm} ({pct(total_precision_similar, total_vlm)})") + prec_total = total_precision_exact + total_precision_similar + print(f" Total correct: {prec_total:4d} / {total_vlm} ({pct(prec_total, total_vlm)})") + print(f" Extra/wrong: {total_precision_extra:4d} / {total_vlm} ({pct(total_precision_extra, total_vlm)})") + + if confusion_counter: + print() + print("--- Similar-Match Confusions (expected -> got) ---") + for (expected, got), count in confusion_counter.most_common(): + print(f" {expected:30s} -> {got:20s} x{count}") + + if missed_counter: + print() + print("--- Most Missed Ground Truth Colors ---") + for color, count in missed_counter.most_common(20): + bar = "#" * min(count, 40) + print(f" {color:30s} {count:3d} {bar}") + + if extra_counter: + print() + print("--- Most Common Extra/Wrong VLM Colors ---") + for color, count in extra_counter.most_common(20): + bar = "#" * min(count, 40) + print(f" {color:30s} {count:3d} {bar}") + + if per_image_results: + tags = Counter(r['tag'] for r in per_image_results) + print() + print("--- Per-Image Verdict ---") + for tag in ['PASS', 'PARTIAL', 'FAIL']: + print(f" {tag:10s} {tags.get(tag, 0):4d}") + + failed = [r for r in per_image_results if r['tag'] == 'FAIL'] + if failed: + print() + print(f"--- Failed Images ({len(failed)}) ---") + for r in failed: + scores = r['scores'] + missed_strs = ["|".join(g) for g in scores['recall_missed']] + print(f" {r['file']}") + print(f" missed: {', '.join(missed_strs)}") + if scores['precision_extra']: + print(f" extra: {', '.join(scores['precision_extra'])}") + + +# --------------------------------------------------------------------------- +# Main +# --------------------------------------------------------------------------- +def main(): + prompt_file = sys.argv[1] if len(sys.argv) > 1 else DEFAULT_PROMPT_FILE + api_key = load_api_key() + + with open(prompt_file, 'r') as f: + prompt = f.read() + + valid_extensions = {'.jpg', '.jpeg', '.png', '.bmp', '.tiff', '.webp'} + image_files = sorted([ + p for p in Path(IMAGES_DIR).iterdir() + if p.suffix.lower() in valid_extensions + ]) + + print(f"Model: {GEMINI_MODEL}") + print(f"Images to process: {len(image_files)}") + print(f"Concurrency: {CONCURRENT_WORKERS} workers") + print(f"Prompt: {prompt_file} ({len(prompt)} chars)") + print("=" * 80) + + # ------------------------------------------------------------------ + # Phase 1: Pre-encode all images + # ------------------------------------------------------------------ + print("Pre-encoding images ... ", end="", flush=True) + t_enc = time.time() + encoded_images = [] + for image_path in image_files: + encoded_images.append(encode_image(str(image_path))) + print(f"{len(encoded_images)} images in {time.time() - t_enc:.1f}s") + + # ------------------------------------------------------------------ + # Phase 2: Submit all API calls concurrently + # ------------------------------------------------------------------ + session = requests.Session() + start_all = time.time() + + print(f"Sending API requests ... ", flush=True) + api_results = [None] * len(image_files) + with concurrent.futures.ThreadPoolExecutor(max_workers=CONCURRENT_WORKERS) as executor: + future_to_idx = {} + for i, (image_data, mime_type) in enumerate(encoded_images): + future = executor.submit( + _api_worker, session, api_key, image_data, mime_type, prompt, + ) + future_to_idx[future] = i + + completed = 0 + for future in concurrent.futures.as_completed(future_to_idx): + idx = future_to_idx[future] + api_results[idx] = future.result() + completed += 1 + print(f"\r {completed}/{len(image_files)} API calls completed", end="", flush=True) + + api_time = time.time() - start_all + print(f" ({api_time:.1f}s total)") + print("=" * 80) + + # ------------------------------------------------------------------ + # Phase 3: Score results in order + # ------------------------------------------------------------------ + total_gt = 0 + total_vlm = 0 + total_recall_exact = 0 + total_recall_similar = 0 + total_recall_missed = 0 + total_precision_exact = 0 + total_precision_similar = 0 + total_precision_extra = 0 + errors = 0 + + confusion_counter = Counter() + missed_counter = Counter() + extra_counter = Counter() + per_image_results = [] + + for i, (image_path, result) in enumerate(zip(image_files, api_results), 1): + gt_groups = parse_ground_truth(image_path.name) + gt_display = ", ".join("|".join(g) for g in gt_groups) if gt_groups else "(none)" + print(f"\n[{i}/{len(image_files)}] {image_path.name}") + print(f" GT: [{gt_display}]") + + if result['error'] is not None: + e = result['error'] + if isinstance(e, requests.exceptions.HTTPError): + print(f" HTTP ERROR: {e}") + else: + print(f" ERROR: {e}") + errors += 1 + continue + + elapsed = result['elapsed'] + + try: + jerseys, vlm_colors = parse_response(result) + + vlm_display = ", ".join(sorted(vlm_colors)) if vlm_colors else "(none)" + print(f" VLM: [{vlm_display}] ({len(jerseys)} jersey(s), {elapsed:.1f}s)") + + if not gt_groups: + print(" -- no ground truth colors (white-only), skipping scoring") + continue + + scores = score_image(gt_groups, vlm_colors) + total_gt += scores['gt_count'] + total_vlm += scores['vlm_count'] + total_recall_exact += scores['recall_exact'] + total_recall_similar += scores['recall_similar'] + total_recall_missed += len(scores['recall_missed']) + total_precision_exact += scores['precision_exact'] + total_precision_similar += scores['precision_similar'] + total_precision_extra += len(scores['precision_extra']) + + for group, got in scores['confusions']: + confusion_counter[("|".join(group), got)] += 1 + for group in scores['recall_missed']: + missed_counter["|".join(group)] += 1 + for ec in scores['precision_extra']: + extra_counter[ec] += 1 + + tag, status_parts = score_and_format(gt_groups, vlm_colors, scores) + print(f" {tag} {', '.join(status_parts)}") + + per_image_results.append({ + 'file': image_path.name, + 'tag': tag, + 'scores': scores, + }) + + except Exception as e: + print(f" PARSE ERROR: {e}") + errors += 1 + + total_time = time.time() - start_all + + print_summary( + GEMINI_MODEL, total_gt, total_vlm, total_recall_exact, + total_recall_similar, total_recall_missed, total_precision_exact, + total_precision_similar, total_precision_extra, confusion_counter, + missed_counter, extra_counter, per_image_results, len(image_files), + errors, total_time, + ) + + +if __name__ == '__main__': + main() diff --git a/uv.lock b/uv.lock new file mode 100644 index 0000000..2e6f4c2 --- /dev/null +++ b/uv.lock @@ -0,0 +1,198 @@ +version = 1 +revision = 3 +requires-python = ">=3.12" + +[[package]] +name = "certifi" +version = "2026.1.4" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/e0/2d/a891ca51311197f6ad14a7ef42e2399f36cf2f9bd44752b3dc4eab60fdc5/certifi-2026.1.4.tar.gz", hash = "sha256:ac726dd470482006e014ad384921ed6438c457018f4b3d204aea4281258b2120", size = 154268, upload-time = "2026-01-04T02:42:41.825Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/e6/ad/3cc14f097111b4de0040c83a525973216457bbeeb63739ef1ed275c1c021/certifi-2026.1.4-py3-none-any.whl", hash = "sha256:9943707519e4add1115f44c2bc244f782c0249876bf51b6599fee1ffbedd685c", size = 152900, upload-time = "2026-01-04T02:42:40.15Z" }, +] + +[[package]] +name = "charset-normalizer" +version = "3.4.4" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/13/69/33ddede1939fdd074bce5434295f38fae7136463422fe4fd3e0e89b98062/charset_normalizer-3.4.4.tar.gz", hash = "sha256:94537985111c35f28720e43603b8e7b43a6ecfb2ce1d3058bbe955b73404e21a", size = 129418, upload-time = "2025-10-14T04:42:32.879Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/f3/85/1637cd4af66fa687396e757dec650f28025f2a2f5a5531a3208dc0ec43f2/charset_normalizer-3.4.4-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:0a98e6759f854bd25a58a73fa88833fba3b7c491169f86ce1180c948ab3fd394", size = 208425, upload-time = "2025-10-14T04:40:53.353Z" }, + { url = "https://files.pythonhosted.org/packages/9d/6a/04130023fef2a0d9c62d0bae2649b69f7b7d8d24ea5536feef50551029df/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b5b290ccc2a263e8d185130284f8501e3e36c5e02750fc6b6bdeb2e9e96f1e25", size = 148162, upload-time = "2025-10-14T04:40:54.558Z" }, + { url = "https://files.pythonhosted.org/packages/78/29/62328d79aa60da22c9e0b9a66539feae06ca0f5a4171ac4f7dc285b83688/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:74bb723680f9f7a6234dcf67aea57e708ec1fbdf5699fb91dfd6f511b0a320ef", size = 144558, upload-time = "2025-10-14T04:40:55.677Z" }, + { url = "https://files.pythonhosted.org/packages/86/bb/b32194a4bf15b88403537c2e120b817c61cd4ecffa9b6876e941c3ee38fe/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:f1e34719c6ed0b92f418c7c780480b26b5d9c50349e9a9af7d76bf757530350d", size = 161497, upload-time = "2025-10-14T04:40:57.217Z" }, + { url = "https://files.pythonhosted.org/packages/19/89/a54c82b253d5b9b111dc74aca196ba5ccfcca8242d0fb64146d4d3183ff1/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:2437418e20515acec67d86e12bf70056a33abdacb5cb1655042f6538d6b085a8", size = 159240, upload-time = "2025-10-14T04:40:58.358Z" }, + { url = "https://files.pythonhosted.org/packages/c0/10/d20b513afe03acc89ec33948320a5544d31f21b05368436d580dec4e234d/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:11d694519d7f29d6cd09f6ac70028dba10f92f6cdd059096db198c283794ac86", size = 153471, upload-time = "2025-10-14T04:40:59.468Z" }, + { url = "https://files.pythonhosted.org/packages/61/fa/fbf177b55bdd727010f9c0a3c49eefa1d10f960e5f09d1d887bf93c2e698/charset_normalizer-3.4.4-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:ac1c4a689edcc530fc9d9aa11f5774b9e2f33f9a0c6a57864e90908f5208d30a", size = 150864, upload-time = "2025-10-14T04:41:00.623Z" }, + { url = "https://files.pythonhosted.org/packages/05/12/9fbc6a4d39c0198adeebbde20b619790e9236557ca59fc40e0e3cebe6f40/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:21d142cc6c0ec30d2efee5068ca36c128a30b0f2c53c1c07bd78cb6bc1d3be5f", size = 150647, upload-time = "2025-10-14T04:41:01.754Z" }, + { url = "https://files.pythonhosted.org/packages/ad/1f/6a9a593d52e3e8c5d2b167daf8c6b968808efb57ef4c210acb907c365bc4/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:5dbe56a36425d26d6cfb40ce79c314a2e4dd6211d51d6d2191c00bed34f354cc", size = 145110, upload-time = "2025-10-14T04:41:03.231Z" }, + { url = "https://files.pythonhosted.org/packages/30/42/9a52c609e72471b0fc54386dc63c3781a387bb4fe61c20231a4ebcd58bdd/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:5bfbb1b9acf3334612667b61bd3002196fe2a1eb4dd74d247e0f2a4d50ec9bbf", size = 162839, upload-time = "2025-10-14T04:41:04.715Z" }, + { url = "https://files.pythonhosted.org/packages/c4/5b/c0682bbf9f11597073052628ddd38344a3d673fda35a36773f7d19344b23/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:d055ec1e26e441f6187acf818b73564e6e6282709e9bcb5b63f5b23068356a15", size = 150667, upload-time = "2025-10-14T04:41:05.827Z" }, + { url = "https://files.pythonhosted.org/packages/e4/24/a41afeab6f990cf2daf6cb8c67419b63b48cf518e4f56022230840c9bfb2/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:af2d8c67d8e573d6de5bc30cdb27e9b95e49115cd9baad5ddbd1a6207aaa82a9", size = 160535, upload-time = "2025-10-14T04:41:06.938Z" }, + { url = "https://files.pythonhosted.org/packages/2a/e5/6a4ce77ed243c4a50a1fecca6aaaab419628c818a49434be428fe24c9957/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:780236ac706e66881f3b7f2f32dfe90507a09e67d1d454c762cf642e6e1586e0", size = 154816, upload-time = "2025-10-14T04:41:08.101Z" }, + { url = "https://files.pythonhosted.org/packages/a8/ef/89297262b8092b312d29cdb2517cb1237e51db8ecef2e9af5edbe7b683b1/charset_normalizer-3.4.4-cp312-cp312-win32.whl", hash = "sha256:5833d2c39d8896e4e19b689ffc198f08ea58116bee26dea51e362ecc7cd3ed26", size = 99694, upload-time = "2025-10-14T04:41:09.23Z" }, + { url = "https://files.pythonhosted.org/packages/3d/2d/1e5ed9dd3b3803994c155cd9aacb60c82c331bad84daf75bcb9c91b3295e/charset_normalizer-3.4.4-cp312-cp312-win_amd64.whl", hash = "sha256:a79cfe37875f822425b89a82333404539ae63dbdddf97f84dcbc3d339aae9525", size = 107131, upload-time = "2025-10-14T04:41:10.467Z" }, + { url = "https://files.pythonhosted.org/packages/d0/d9/0ed4c7098a861482a7b6a95603edce4c0d9db2311af23da1fb2b75ec26fc/charset_normalizer-3.4.4-cp312-cp312-win_arm64.whl", hash = "sha256:376bec83a63b8021bb5c8ea75e21c4ccb86e7e45ca4eb81146091b56599b80c3", size = 100390, upload-time = "2025-10-14T04:41:11.915Z" }, + { url = "https://files.pythonhosted.org/packages/97/45/4b3a1239bbacd321068ea6e7ac28875b03ab8bc0aa0966452db17cd36714/charset_normalizer-3.4.4-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:e1f185f86a6f3403aa2420e815904c67b2f9ebc443f045edd0de921108345794", size = 208091, upload-time = "2025-10-14T04:41:13.346Z" }, + { url = "https://files.pythonhosted.org/packages/7d/62/73a6d7450829655a35bb88a88fca7d736f9882a27eacdca2c6d505b57e2e/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6b39f987ae8ccdf0d2642338faf2abb1862340facc796048b604ef14919e55ed", size = 147936, upload-time = "2025-10-14T04:41:14.461Z" }, + { url = "https://files.pythonhosted.org/packages/89/c5/adb8c8b3d6625bef6d88b251bbb0d95f8205831b987631ab0c8bb5d937c2/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:3162d5d8ce1bb98dd51af660f2121c55d0fa541b46dff7bb9b9f86ea1d87de72", size = 144180, upload-time = "2025-10-14T04:41:15.588Z" }, + { url = "https://files.pythonhosted.org/packages/91/ed/9706e4070682d1cc219050b6048bfd293ccf67b3d4f5a4f39207453d4b99/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:81d5eb2a312700f4ecaa977a8235b634ce853200e828fbadf3a9c50bab278328", size = 161346, upload-time = "2025-10-14T04:41:16.738Z" }, + { url = "https://files.pythonhosted.org/packages/d5/0d/031f0d95e4972901a2f6f09ef055751805ff541511dc1252ba3ca1f80cf5/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:5bd2293095d766545ec1a8f612559f6b40abc0eb18bb2f5d1171872d34036ede", size = 158874, upload-time = "2025-10-14T04:41:17.923Z" }, + { url = "https://files.pythonhosted.org/packages/f5/83/6ab5883f57c9c801ce5e5677242328aa45592be8a00644310a008d04f922/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a8a8b89589086a25749f471e6a900d3f662d1d3b6e2e59dcecf787b1cc3a1894", size = 153076, upload-time = "2025-10-14T04:41:19.106Z" }, + { url = "https://files.pythonhosted.org/packages/75/1e/5ff781ddf5260e387d6419959ee89ef13878229732732ee73cdae01800f2/charset_normalizer-3.4.4-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:bc7637e2f80d8530ee4a78e878bce464f70087ce73cf7c1caf142416923b98f1", size = 150601, upload-time = "2025-10-14T04:41:20.245Z" }, + { url = "https://files.pythonhosted.org/packages/d7/57/71be810965493d3510a6ca79b90c19e48696fb1ff964da319334b12677f0/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:f8bf04158c6b607d747e93949aa60618b61312fe647a6369f88ce2ff16043490", size = 150376, upload-time = "2025-10-14T04:41:21.398Z" }, + { url = "https://files.pythonhosted.org/packages/e5/d5/c3d057a78c181d007014feb7e9f2e65905a6c4ef182c0ddf0de2924edd65/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:554af85e960429cf30784dd47447d5125aaa3b99a6f0683589dbd27e2f45da44", size = 144825, upload-time = "2025-10-14T04:41:22.583Z" }, + { url = "https://files.pythonhosted.org/packages/e6/8c/d0406294828d4976f275ffbe66f00266c4b3136b7506941d87c00cab5272/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:74018750915ee7ad843a774364e13a3db91682f26142baddf775342c3f5b1133", size = 162583, upload-time = "2025-10-14T04:41:23.754Z" }, + { url = "https://files.pythonhosted.org/packages/d7/24/e2aa1f18c8f15c4c0e932d9287b8609dd30ad56dbe41d926bd846e22fb8d/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:c0463276121fdee9c49b98908b3a89c39be45d86d1dbaa22957e38f6321d4ce3", size = 150366, upload-time = "2025-10-14T04:41:25.27Z" }, + { url = "https://files.pythonhosted.org/packages/e4/5b/1e6160c7739aad1e2df054300cc618b06bf784a7a164b0f238360721ab86/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:362d61fd13843997c1c446760ef36f240cf81d3ebf74ac62652aebaf7838561e", size = 160300, upload-time = "2025-10-14T04:41:26.725Z" }, + { url = "https://files.pythonhosted.org/packages/7a/10/f882167cd207fbdd743e55534d5d9620e095089d176d55cb22d5322f2afd/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:9a26f18905b8dd5d685d6d07b0cdf98a79f3c7a918906af7cc143ea2e164c8bc", size = 154465, upload-time = "2025-10-14T04:41:28.322Z" }, + { url = "https://files.pythonhosted.org/packages/89/66/c7a9e1b7429be72123441bfdbaf2bc13faab3f90b933f664db506dea5915/charset_normalizer-3.4.4-cp313-cp313-win32.whl", hash = "sha256:9b35f4c90079ff2e2edc5b26c0c77925e5d2d255c42c74fdb70fb49b172726ac", size = 99404, upload-time = "2025-10-14T04:41:29.95Z" }, + { url = "https://files.pythonhosted.org/packages/c4/26/b9924fa27db384bdcd97ab83b4f0a8058d96ad9626ead570674d5e737d90/charset_normalizer-3.4.4-cp313-cp313-win_amd64.whl", hash = "sha256:b435cba5f4f750aa6c0a0d92c541fb79f69a387c91e61f1795227e4ed9cece14", size = 107092, upload-time = "2025-10-14T04:41:31.188Z" }, + { url = "https://files.pythonhosted.org/packages/af/8f/3ed4bfa0c0c72a7ca17f0380cd9e4dd842b09f664e780c13cff1dcf2ef1b/charset_normalizer-3.4.4-cp313-cp313-win_arm64.whl", hash = "sha256:542d2cee80be6f80247095cc36c418f7bddd14f4a6de45af91dfad36d817bba2", size = 100408, upload-time = "2025-10-14T04:41:32.624Z" }, + { url = "https://files.pythonhosted.org/packages/2a/35/7051599bd493e62411d6ede36fd5af83a38f37c4767b92884df7301db25d/charset_normalizer-3.4.4-cp314-cp314-macosx_10_13_universal2.whl", hash = "sha256:da3326d9e65ef63a817ecbcc0df6e94463713b754fe293eaa03da99befb9a5bd", size = 207746, upload-time = "2025-10-14T04:41:33.773Z" }, + { url = "https://files.pythonhosted.org/packages/10/9a/97c8d48ef10d6cd4fcead2415523221624bf58bcf68a802721a6bc807c8f/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8af65f14dc14a79b924524b1e7fffe304517b2bff5a58bf64f30b98bbc5079eb", size = 147889, upload-time = "2025-10-14T04:41:34.897Z" }, + { url = "https://files.pythonhosted.org/packages/10/bf/979224a919a1b606c82bd2c5fa49b5c6d5727aa47b4312bb27b1734f53cd/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:74664978bb272435107de04e36db5a9735e78232b85b77d45cfb38f758efd33e", size = 143641, upload-time = "2025-10-14T04:41:36.116Z" }, + { url = "https://files.pythonhosted.org/packages/ba/33/0ad65587441fc730dc7bd90e9716b30b4702dc7b617e6ba4997dc8651495/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:752944c7ffbfdd10c074dc58ec2d5a8a4cd9493b314d367c14d24c17684ddd14", size = 160779, upload-time = "2025-10-14T04:41:37.229Z" }, + { url = "https://files.pythonhosted.org/packages/67/ed/331d6b249259ee71ddea93f6f2f0a56cfebd46938bde6fcc6f7b9a3d0e09/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d1f13550535ad8cff21b8d757a3257963e951d96e20ec82ab44bc64aeb62a191", size = 159035, upload-time = "2025-10-14T04:41:38.368Z" }, + { url = "https://files.pythonhosted.org/packages/67/ff/f6b948ca32e4f2a4576aa129d8bed61f2e0543bf9f5f2b7fc3758ed005c9/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ecaae4149d99b1c9e7b88bb03e3221956f68fd6d50be2ef061b2381b61d20838", size = 152542, upload-time = "2025-10-14T04:41:39.862Z" }, + { url = "https://files.pythonhosted.org/packages/16/85/276033dcbcc369eb176594de22728541a925b2632f9716428c851b149e83/charset_normalizer-3.4.4-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:cb6254dc36b47a990e59e1068afacdcd02958bdcce30bb50cc1700a8b9d624a6", size = 149524, upload-time = "2025-10-14T04:41:41.319Z" }, + { url = "https://files.pythonhosted.org/packages/9e/f2/6a2a1f722b6aba37050e626530a46a68f74e63683947a8acff92569f979a/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:c8ae8a0f02f57a6e61203a31428fa1d677cbe50c93622b4149d5c0f319c1d19e", size = 150395, upload-time = "2025-10-14T04:41:42.539Z" }, + { url = "https://files.pythonhosted.org/packages/60/bb/2186cb2f2bbaea6338cad15ce23a67f9b0672929744381e28b0592676824/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:47cc91b2f4dd2833fddaedd2893006b0106129d4b94fdb6af1f4ce5a9965577c", size = 143680, upload-time = "2025-10-14T04:41:43.661Z" }, + { url = "https://files.pythonhosted.org/packages/7d/a5/bf6f13b772fbb2a90360eb620d52ed8f796f3c5caee8398c3b2eb7b1c60d/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:82004af6c302b5d3ab2cfc4cc5f29db16123b1a8417f2e25f9066f91d4411090", size = 162045, upload-time = "2025-10-14T04:41:44.821Z" }, + { url = "https://files.pythonhosted.org/packages/df/c5/d1be898bf0dc3ef9030c3825e5d3b83f2c528d207d246cbabe245966808d/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:2b7d8f6c26245217bd2ad053761201e9f9680f8ce52f0fcd8d0755aeae5b2152", size = 149687, upload-time = "2025-10-14T04:41:46.442Z" }, + { url = "https://files.pythonhosted.org/packages/a5/42/90c1f7b9341eef50c8a1cb3f098ac43b0508413f33affd762855f67a410e/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:799a7a5e4fb2d5898c60b640fd4981d6a25f1c11790935a44ce38c54e985f828", size = 160014, upload-time = "2025-10-14T04:41:47.631Z" }, + { url = "https://files.pythonhosted.org/packages/76/be/4d3ee471e8145d12795ab655ece37baed0929462a86e72372fd25859047c/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:99ae2cffebb06e6c22bdc25801d7b30f503cc87dbd283479e7b606f70aff57ec", size = 154044, upload-time = "2025-10-14T04:41:48.81Z" }, + { url = "https://files.pythonhosted.org/packages/b0/6f/8f7af07237c34a1defe7defc565a9bc1807762f672c0fde711a4b22bf9c0/charset_normalizer-3.4.4-cp314-cp314-win32.whl", hash = "sha256:f9d332f8c2a2fcbffe1378594431458ddbef721c1769d78e2cbc06280d8155f9", size = 99940, upload-time = "2025-10-14T04:41:49.946Z" }, + { url = "https://files.pythonhosted.org/packages/4b/51/8ade005e5ca5b0d80fb4aff72a3775b325bdc3d27408c8113811a7cbe640/charset_normalizer-3.4.4-cp314-cp314-win_amd64.whl", hash = "sha256:8a6562c3700cce886c5be75ade4a5db4214fda19fede41d9792d100288d8f94c", size = 107104, upload-time = "2025-10-14T04:41:51.051Z" }, + { url = "https://files.pythonhosted.org/packages/da/5f/6b8f83a55bb8278772c5ae54a577f3099025f9ade59d0136ac24a0df4bde/charset_normalizer-3.4.4-cp314-cp314-win_arm64.whl", hash = "sha256:de00632ca48df9daf77a2c65a484531649261ec9f25489917f09e455cb09ddb2", size = 100743, upload-time = "2025-10-14T04:41:52.122Z" }, + { url = "https://files.pythonhosted.org/packages/0a/4c/925909008ed5a988ccbb72dcc897407e5d6d3bd72410d69e051fc0c14647/charset_normalizer-3.4.4-py3-none-any.whl", hash = "sha256:7a32c560861a02ff789ad905a2fe94e3f840803362c84fecf1851cb4cf3dc37f", size = 53402, upload-time = "2025-10-14T04:42:31.76Z" }, +] + +[[package]] +name = "idna" +version = "3.11" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/6f/6d/0703ccc57f3a7233505399edb88de3cbd678da106337b9fcde432b65ed60/idna-3.11.tar.gz", hash = "sha256:795dafcc9c04ed0c1fb032c2aa73654d8e8c5023a7df64a53f39190ada629902", size = 194582, upload-time = "2025-10-12T14:55:20.501Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/0e/61/66938bbb5fc52dbdf84594873d5b51fb1f7c7794e9c0f5bd885f30bc507b/idna-3.11-py3-none-any.whl", hash = "sha256:771a87f49d9defaf64091e6e6fe9c18d4833f140bd19464795bc32d966ca37ea", size = 71008, upload-time = "2025-10-12T14:55:18.883Z" }, +] + +[[package]] +name = "jersey-test" +version = "0.1.0" +source = { virtual = "." } +dependencies = [ + { name = "numpy" }, + { name = "opencv-python" }, + { name = "requests" }, +] + +[package.metadata] +requires-dist = [ + { name = "numpy", specifier = ">=1.24.0" }, + { name = "opencv-python", specifier = ">=4.8.0" }, + { name = "requests", specifier = ">=2.28.0" }, +] + +[[package]] +name = "numpy" +version = "2.4.2" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/57/fd/0005efbd0af48e55eb3c7208af93f2862d4b1a56cd78e84309a2d959208d/numpy-2.4.2.tar.gz", hash = "sha256:659a6107e31a83c4e33f763942275fd278b21d095094044eb35569e86a21ddae", size = 20723651, upload-time = "2026-01-31T23:13:10.135Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/51/6e/6f394c9c77668153e14d4da83bcc247beb5952f6ead7699a1a2992613bea/numpy-2.4.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:21982668592194c609de53ba4933a7471880ccbaadcc52352694a59ecc860b3a", size = 16667963, upload-time = "2026-01-31T23:10:52.147Z" }, + { url = "https://files.pythonhosted.org/packages/1f/f8/55483431f2b2fd015ae6ed4fe62288823ce908437ed49db5a03d15151678/numpy-2.4.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40397bda92382fcec844066efb11f13e1c9a3e2a8e8f318fb72ed8b6db9f60f1", size = 14693571, upload-time = "2026-01-31T23:10:54.789Z" }, + { url = "https://files.pythonhosted.org/packages/2f/20/18026832b1845cdc82248208dd929ca14c9d8f2bac391f67440707fff27c/numpy-2.4.2-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:b3a24467af63c67829bfaa61eecf18d5432d4f11992688537be59ecd6ad32f5e", size = 5203469, upload-time = "2026-01-31T23:10:57.343Z" }, + { url = "https://files.pythonhosted.org/packages/7d/33/2eb97c8a77daaba34eaa3fa7241a14ac5f51c46a6bd5911361b644c4a1e2/numpy-2.4.2-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:805cc8de9fd6e7a22da5aed858e0ab16be5a4db6c873dde1d7451c541553aa27", size = 6550820, upload-time = "2026-01-31T23:10:59.429Z" }, + { url = "https://files.pythonhosted.org/packages/b1/91/b97fdfd12dc75b02c44e26c6638241cc004d4079a0321a69c62f51470c4c/numpy-2.4.2-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6d82351358ffbcdcd7b686b90742a9b86632d6c1c051016484fa0b326a0a1548", size = 15663067, upload-time = "2026-01-31T23:11:01.291Z" }, + { url = "https://files.pythonhosted.org/packages/f5/c6/a18e59f3f0b8071cc85cbc8d80cd02d68aa9710170b2553a117203d46936/numpy-2.4.2-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9e35d3e0144137d9fdae62912e869136164534d64a169f86438bc9561b6ad49f", size = 16619782, upload-time = "2026-01-31T23:11:03.669Z" }, + { url = "https://files.pythonhosted.org/packages/b7/83/9751502164601a79e18847309f5ceec0b1446d7b6aa12305759b72cf98b2/numpy-2.4.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:adb6ed2ad29b9e15321d167d152ee909ec73395901b70936f029c3bc6d7f4460", size = 17013128, upload-time = "2026-01-31T23:11:05.913Z" }, + { url = "https://files.pythonhosted.org/packages/61/c4/c4066322256ec740acc1c8923a10047818691d2f8aec254798f3dd90f5f2/numpy-2.4.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:8906e71fd8afcb76580404e2a950caef2685df3d2a57fe82a86ac8d33cc007ba", size = 18345324, upload-time = "2026-01-31T23:11:08.248Z" }, + { url = "https://files.pythonhosted.org/packages/ab/af/6157aa6da728fa4525a755bfad486ae7e3f76d4c1864138003eb84328497/numpy-2.4.2-cp312-cp312-win32.whl", hash = "sha256:ec055f6dae239a6299cace477b479cca2fc125c5675482daf1dd886933a1076f", size = 5960282, upload-time = "2026-01-31T23:11:10.497Z" }, + { url = "https://files.pythonhosted.org/packages/92/0f/7ceaaeaacb40567071e94dbf2c9480c0ae453d5bb4f52bea3892c39dc83c/numpy-2.4.2-cp312-cp312-win_amd64.whl", hash = "sha256:209fae046e62d0ce6435fcfe3b1a10537e858249b3d9b05829e2a05218296a85", size = 12314210, upload-time = "2026-01-31T23:11:12.176Z" }, + { url = "https://files.pythonhosted.org/packages/2f/a3/56c5c604fae6dd40fa2ed3040d005fca97e91bd320d232ac9931d77ba13c/numpy-2.4.2-cp312-cp312-win_arm64.whl", hash = "sha256:fbde1b0c6e81d56f5dccd95dd4a711d9b95df1ae4009a60887e56b27e8d903fa", size = 10220171, upload-time = "2026-01-31T23:11:14.684Z" }, + { url = "https://files.pythonhosted.org/packages/a1/22/815b9fe25d1d7ae7d492152adbc7226d3eff731dffc38fe970589fcaaa38/numpy-2.4.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:25f2059807faea4b077a2b6837391b5d830864b3543627f381821c646f31a63c", size = 16663696, upload-time = "2026-01-31T23:11:17.516Z" }, + { url = "https://files.pythonhosted.org/packages/09/f0/817d03a03f93ba9c6c8993de509277d84e69f9453601915e4a69554102a1/numpy-2.4.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:bd3a7a9f5847d2fb8c2c6d1c862fa109c31a9abeca1a3c2bd5a64572955b2979", size = 14688322, upload-time = "2026-01-31T23:11:19.883Z" }, + { url = "https://files.pythonhosted.org/packages/da/b4/f805ab79293c728b9a99438775ce51885fd4f31b76178767cfc718701a39/numpy-2.4.2-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:8e4549f8a3c6d13d55041925e912bfd834285ef1dd64d6bc7d542583355e2e98", size = 5198157, upload-time = "2026-01-31T23:11:22.375Z" }, + { url = "https://files.pythonhosted.org/packages/74/09/826e4289844eccdcd64aac27d13b0fd3f32039915dd5b9ba01baae1f436c/numpy-2.4.2-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:aea4f66ff44dfddf8c2cffd66ba6538c5ec67d389285292fe428cb2c738c8aef", size = 6546330, upload-time = "2026-01-31T23:11:23.958Z" }, + { url = "https://files.pythonhosted.org/packages/19/fb/cbfdbfa3057a10aea5422c558ac57538e6acc87ec1669e666d32ac198da7/numpy-2.4.2-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c3cd545784805de05aafe1dde61752ea49a359ccba9760c1e5d1c88a93bbf2b7", size = 15660968, upload-time = "2026-01-31T23:11:25.713Z" }, + { url = "https://files.pythonhosted.org/packages/04/dc/46066ce18d01645541f0186877377b9371b8fa8017fa8262002b4ef22612/numpy-2.4.2-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d0d9b7c93578baafcbc5f0b83eaf17b79d345c6f36917ba0c67f45226911d499", size = 16607311, upload-time = "2026-01-31T23:11:28.117Z" }, + { url = "https://files.pythonhosted.org/packages/14/d9/4b5adfc39a43fa6bf918c6d544bc60c05236cc2f6339847fc5b35e6cb5b0/numpy-2.4.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:f74f0f7779cc7ae07d1810aab8ac6b1464c3eafb9e283a40da7309d5e6e48fbb", size = 17012850, upload-time = "2026-01-31T23:11:30.888Z" }, + { url = "https://files.pythonhosted.org/packages/b7/20/adb6e6adde6d0130046e6fdfb7675cc62bc2f6b7b02239a09eb58435753d/numpy-2.4.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:c7ac672d699bf36275c035e16b65539931347d68b70667d28984c9fb34e07fa7", size = 18334210, upload-time = "2026-01-31T23:11:33.214Z" }, + { url = "https://files.pythonhosted.org/packages/78/0e/0a73b3dff26803a8c02baa76398015ea2a5434d9b8265a7898a6028c1591/numpy-2.4.2-cp313-cp313-win32.whl", hash = "sha256:8e9afaeb0beff068b4d9cd20d322ba0ee1cecfb0b08db145e4ab4dd44a6b5110", size = 5958199, upload-time = "2026-01-31T23:11:35.385Z" }, + { url = "https://files.pythonhosted.org/packages/43/bc/6352f343522fcb2c04dbaf94cb30cca6fd32c1a750c06ad6231b4293708c/numpy-2.4.2-cp313-cp313-win_amd64.whl", hash = "sha256:7df2de1e4fba69a51c06c28f5a3de36731eb9639feb8e1cf7e4a7b0daf4cf622", size = 12310848, upload-time = "2026-01-31T23:11:38.001Z" }, + { url = "https://files.pythonhosted.org/packages/6e/8d/6da186483e308da5da1cc6918ce913dcfe14ffde98e710bfeff2a6158d4e/numpy-2.4.2-cp313-cp313-win_arm64.whl", hash = "sha256:0fece1d1f0a89c16b03442eae5c56dc0be0c7883b5d388e0c03f53019a4bfd71", size = 10221082, upload-time = "2026-01-31T23:11:40.392Z" }, + { url = "https://files.pythonhosted.org/packages/25/a1/9510aa43555b44781968935c7548a8926274f815de42ad3997e9e83680dd/numpy-2.4.2-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:5633c0da313330fd20c484c78cdd3f9b175b55e1a766c4a174230c6b70ad8262", size = 14815866, upload-time = "2026-01-31T23:11:42.495Z" }, + { url = "https://files.pythonhosted.org/packages/36/30/6bbb5e76631a5ae46e7923dd16ca9d3f1c93cfa8d4ed79a129814a9d8db3/numpy-2.4.2-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:d9f64d786b3b1dd742c946c42d15b07497ed14af1a1f3ce840cce27daa0ce913", size = 5325631, upload-time = "2026-01-31T23:11:44.7Z" }, + { url = "https://files.pythonhosted.org/packages/46/00/3a490938800c1923b567b3a15cd17896e68052e2145d8662aaf3e1ffc58f/numpy-2.4.2-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:b21041e8cb6a1eb5312dd1d2f80a94d91efffb7a06b70597d44f1bd2dfc315ab", size = 6646254, upload-time = "2026-01-31T23:11:46.341Z" }, + { url = "https://files.pythonhosted.org/packages/d3/e9/fac0890149898a9b609caa5af7455a948b544746e4b8fe7c212c8edd71f8/numpy-2.4.2-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:00ab83c56211a1d7c07c25e3217ea6695e50a3e2f255053686b081dc0b091a82", size = 15720138, upload-time = "2026-01-31T23:11:48.082Z" }, + { url = "https://files.pythonhosted.org/packages/ea/5c/08887c54e68e1e28df53709f1893ce92932cc6f01f7c3d4dc952f61ffd4e/numpy-2.4.2-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2fb882da679409066b4603579619341c6d6898fc83a8995199d5249f986e8e8f", size = 16655398, upload-time = "2026-01-31T23:11:50.293Z" }, + { url = "https://files.pythonhosted.org/packages/4d/89/253db0fa0e66e9129c745e4ef25631dc37d5f1314dad2b53e907b8538e6d/numpy-2.4.2-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:66cb9422236317f9d44b67b4d18f44efe6e9c7f8794ac0462978513359461554", size = 17079064, upload-time = "2026-01-31T23:11:52.927Z" }, + { url = "https://files.pythonhosted.org/packages/2a/d5/cbade46ce97c59c6c3da525e8d95b7abe8a42974a1dc5c1d489c10433e88/numpy-2.4.2-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:0f01dcf33e73d80bd8dc0f20a71303abbafa26a19e23f6b68d1aa9990af90257", size = 18379680, upload-time = "2026-01-31T23:11:55.22Z" }, + { url = "https://files.pythonhosted.org/packages/40/62/48f99ae172a4b63d981babe683685030e8a3df4f246c893ea5c6ef99f018/numpy-2.4.2-cp313-cp313t-win32.whl", hash = "sha256:52b913ec40ff7ae845687b0b34d8d93b60cb66dcee06996dd5c99f2fc9328657", size = 6082433, upload-time = "2026-01-31T23:11:58.096Z" }, + { url = "https://files.pythonhosted.org/packages/07/38/e054a61cfe48ad9f1ed0d188e78b7e26859d0b60ef21cd9de4897cdb5326/numpy-2.4.2-cp313-cp313t-win_amd64.whl", hash = "sha256:5eea80d908b2c1f91486eb95b3fb6fab187e569ec9752ab7d9333d2e66bf2d6b", size = 12451181, upload-time = "2026-01-31T23:11:59.782Z" }, + { url = "https://files.pythonhosted.org/packages/6e/a4/a05c3a6418575e185dd84d0b9680b6bb2e2dc3e4202f036b7b4e22d6e9dc/numpy-2.4.2-cp313-cp313t-win_arm64.whl", hash = "sha256:fd49860271d52127d61197bb50b64f58454e9f578cb4b2c001a6de8b1f50b0b1", size = 10290756, upload-time = "2026-01-31T23:12:02.438Z" }, + { url = "https://files.pythonhosted.org/packages/18/88/b7df6050bf18fdcfb7046286c6535cabbdd2064a3440fca3f069d319c16e/numpy-2.4.2-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:444be170853f1f9d528428eceb55f12918e4fda5d8805480f36a002f1415e09b", size = 16663092, upload-time = "2026-01-31T23:12:04.521Z" }, + { url = "https://files.pythonhosted.org/packages/25/7a/1fee4329abc705a469a4afe6e69b1ef7e915117747886327104a8493a955/numpy-2.4.2-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:d1240d50adff70c2a88217698ca844723068533f3f5c5fa6ee2e3220e3bdb000", size = 14698770, upload-time = "2026-01-31T23:12:06.96Z" }, + { url = "https://files.pythonhosted.org/packages/fb/0b/f9e49ba6c923678ad5bc38181c08ac5e53b7a5754dbca8e581aa1a56b1ff/numpy-2.4.2-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:7cdde6de52fb6664b00b056341265441192d1291c130e99183ec0d4b110ff8b1", size = 5208562, upload-time = "2026-01-31T23:12:09.632Z" }, + { url = "https://files.pythonhosted.org/packages/7d/12/d7de8f6f53f9bb76997e5e4c069eda2051e3fe134e9181671c4391677bb2/numpy-2.4.2-cp314-cp314-macosx_14_0_x86_64.whl", hash = "sha256:cda077c2e5b780200b6b3e09d0b42205a3d1c68f30c6dceb90401c13bff8fe74", size = 6543710, upload-time = "2026-01-31T23:12:11.969Z" }, + { url = "https://files.pythonhosted.org/packages/09/63/c66418c2e0268a31a4cf8a8b512685748200f8e8e8ec6c507ce14e773529/numpy-2.4.2-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d30291931c915b2ab5717c2974bb95ee891a1cf22ebc16a8006bd59cd210d40a", size = 15677205, upload-time = "2026-01-31T23:12:14.33Z" }, + { url = "https://files.pythonhosted.org/packages/5d/6c/7f237821c9642fb2a04d2f1e88b4295677144ca93285fd76eff3bcba858d/numpy-2.4.2-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:bba37bc29d4d85761deed3954a1bc62be7cf462b9510b51d367b769a8c8df325", size = 16611738, upload-time = "2026-01-31T23:12:16.525Z" }, + { url = "https://files.pythonhosted.org/packages/c2/a7/39c4cdda9f019b609b5c473899d87abff092fc908cfe4d1ecb2fcff453b0/numpy-2.4.2-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:b2f0073ed0868db1dcd86e052d37279eef185b9c8db5bf61f30f46adac63c909", size = 17028888, upload-time = "2026-01-31T23:12:19.306Z" }, + { url = "https://files.pythonhosted.org/packages/da/b3/e84bb64bdfea967cc10950d71090ec2d84b49bc691df0025dddb7c26e8e3/numpy-2.4.2-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:7f54844851cdb630ceb623dcec4db3240d1ac13d4990532446761baede94996a", size = 18339556, upload-time = "2026-01-31T23:12:21.816Z" }, + { url = "https://files.pythonhosted.org/packages/88/f5/954a291bc1192a27081706862ac62bb5920fbecfbaa302f64682aa90beed/numpy-2.4.2-cp314-cp314-win32.whl", hash = "sha256:12e26134a0331d8dbd9351620f037ec470b7c75929cb8a1537f6bfe411152a1a", size = 6006899, upload-time = "2026-01-31T23:12:24.14Z" }, + { url = "https://files.pythonhosted.org/packages/05/cb/eff72a91b2efdd1bc98b3b8759f6a1654aa87612fc86e3d87d6fe4f948c4/numpy-2.4.2-cp314-cp314-win_amd64.whl", hash = "sha256:068cdb2d0d644cdb45670810894f6a0600797a69c05f1ac478e8d31670b8ee75", size = 12443072, upload-time = "2026-01-31T23:12:26.33Z" }, + { url = "https://files.pythonhosted.org/packages/37/75/62726948db36a56428fce4ba80a115716dc4fad6a3a4352487f8bb950966/numpy-2.4.2-cp314-cp314-win_arm64.whl", hash = "sha256:6ed0be1ee58eef41231a5c943d7d1375f093142702d5723ca2eb07db9b934b05", size = 10494886, upload-time = "2026-01-31T23:12:28.488Z" }, + { url = "https://files.pythonhosted.org/packages/36/2f/ee93744f1e0661dc267e4b21940870cabfae187c092e1433b77b09b50ac4/numpy-2.4.2-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:98f16a80e917003a12c0580f97b5f875853ebc33e2eaa4bccfc8201ac6869308", size = 14818567, upload-time = "2026-01-31T23:12:30.709Z" }, + { url = "https://files.pythonhosted.org/packages/a7/24/6535212add7d76ff938d8bdc654f53f88d35cddedf807a599e180dcb8e66/numpy-2.4.2-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:20abd069b9cda45874498b245c8015b18ace6de8546bf50dfa8cea1696ed06ef", size = 5328372, upload-time = "2026-01-31T23:12:32.962Z" }, + { url = "https://files.pythonhosted.org/packages/5e/9d/c48f0a035725f925634bf6b8994253b43f2047f6778a54147d7e213bc5a7/numpy-2.4.2-cp314-cp314t-macosx_14_0_x86_64.whl", hash = "sha256:e98c97502435b53741540a5717a6749ac2ada901056c7db951d33e11c885cc7d", size = 6649306, upload-time = "2026-01-31T23:12:34.797Z" }, + { url = "https://files.pythonhosted.org/packages/81/05/7c73a9574cd4a53a25907bad38b59ac83919c0ddc8234ec157f344d57d9a/numpy-2.4.2-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:da6cad4e82cb893db4b69105c604d805e0c3ce11501a55b5e9f9083b47d2ffe8", size = 15722394, upload-time = "2026-01-31T23:12:36.565Z" }, + { url = "https://files.pythonhosted.org/packages/35/fa/4de10089f21fc7d18442c4a767ab156b25c2a6eaf187c0db6d9ecdaeb43f/numpy-2.4.2-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9e4424677ce4b47fe73c8b5556d876571f7c6945d264201180db2dc34f676ab5", size = 16653343, upload-time = "2026-01-31T23:12:39.188Z" }, + { url = "https://files.pythonhosted.org/packages/b8/f9/d33e4ffc857f3763a57aa85650f2e82486832d7492280ac21ba9efda80da/numpy-2.4.2-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:2b8f157c8a6f20eb657e240f8985cc135598b2b46985c5bccbde7616dc9c6b1e", size = 17078045, upload-time = "2026-01-31T23:12:42.041Z" }, + { url = "https://files.pythonhosted.org/packages/c8/b8/54bdb43b6225badbea6389fa038c4ef868c44f5890f95dd530a218706da3/numpy-2.4.2-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:5daf6f3914a733336dab21a05cdec343144600e964d2fcdabaac0c0269874b2a", size = 18380024, upload-time = "2026-01-31T23:12:44.331Z" }, + { url = "https://files.pythonhosted.org/packages/a5/55/6e1a61ded7af8df04016d81b5b02daa59f2ea9252ee0397cb9f631efe9e5/numpy-2.4.2-cp314-cp314t-win32.whl", hash = "sha256:8c50dd1fc8826f5b26a5ee4d77ca55d88a895f4e4819c7ecc2a9f5905047a443", size = 6153937, upload-time = "2026-01-31T23:12:47.229Z" }, + { url = "https://files.pythonhosted.org/packages/45/aa/fa6118d1ed6d776b0983f3ceac9b1a5558e80df9365b1c3aa6d42bf9eee4/numpy-2.4.2-cp314-cp314t-win_amd64.whl", hash = "sha256:fcf92bee92742edd401ba41135185866f7026c502617f422eb432cfeca4fe236", size = 12631844, upload-time = "2026-01-31T23:12:48.997Z" }, + { url = "https://files.pythonhosted.org/packages/32/0a/2ec5deea6dcd158f254a7b372fb09cfba5719419c8d66343bab35237b3fb/numpy-2.4.2-cp314-cp314t-win_arm64.whl", hash = "sha256:1f92f53998a17265194018d1cc321b2e96e900ca52d54c7c77837b71b9465181", size = 10565379, upload-time = "2026-01-31T23:12:51.345Z" }, +] + +[[package]] +name = "opencv-python" +version = "4.13.0.92" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "numpy" }, +] +wheels = [ + { url = "https://files.pythonhosted.org/packages/fc/6f/5a28fef4c4a382be06afe3938c64cc168223016fa520c5abaf37e8862aa5/opencv_python-4.13.0.92-cp37-abi3-macosx_13_0_arm64.whl", hash = "sha256:caf60c071ec391ba51ed00a4a920f996d0b64e3e46068aac1f646b5de0326a19", size = 46247052, upload-time = "2026-02-05T07:01:25.046Z" }, + { url = "https://files.pythonhosted.org/packages/08/ac/6c98c44c650b8114a0fb901691351cfb3956d502e8e9b5cd27f4ee7fbf2f/opencv_python-4.13.0.92-cp37-abi3-macosx_14_0_x86_64.whl", hash = "sha256:5868a8c028a0b37561579bfb8ac1875babdc69546d236249fff296a8c010ccf9", size = 32568781, upload-time = "2026-02-05T07:01:41.379Z" }, + { url = "https://files.pythonhosted.org/packages/3e/51/82fed528b45173bf629fa44effb76dff8bc9f4eeaee759038362dfa60237/opencv_python-4.13.0.92-cp37-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:0bc2596e68f972ca452d80f444bc404e08807d021fbba40df26b61b18e01838a", size = 47685527, upload-time = "2026-02-05T06:59:11.24Z" }, + { url = "https://files.pythonhosted.org/packages/db/07/90b34a8e2cf9c50fe8ed25cac9011cde0676b4d9d9c973751ac7616223a2/opencv_python-4.13.0.92-cp37-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:402033cddf9d294693094de5ef532339f14ce821da3ad7df7c9f6e8316da32cf", size = 70460872, upload-time = "2026-02-05T06:59:19.162Z" }, + { url = "https://files.pythonhosted.org/packages/02/6d/7a9cc719b3eaf4377b9c2e3edeb7ed3a81de41f96421510c0a169ca3cfd4/opencv_python-4.13.0.92-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:bccaabf9eb7f897ca61880ce2869dcd9b25b72129c28478e7f2a5e8dee945616", size = 46708208, upload-time = "2026-02-05T06:59:15.419Z" }, + { url = "https://files.pythonhosted.org/packages/fd/55/b3b49a1b97aabcfbbd6c7326df9cb0b6fa0c0aefa8e89d500939e04aa229/opencv_python-4.13.0.92-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:620d602b8f7d8b8dab5f4b99c6eb353e78d3fb8b0f53db1bd258bb1aa001c1d5", size = 72927042, upload-time = "2026-02-05T06:59:23.389Z" }, + { url = "https://files.pythonhosted.org/packages/fb/17/de5458312bcb07ddf434d7bfcb24bb52c59635ad58c6e7c751b48949b009/opencv_python-4.13.0.92-cp37-abi3-win32.whl", hash = "sha256:372fe164a3148ac1ca51e5f3ad0541a4a276452273f503441d718fab9c5e5f59", size = 30932638, upload-time = "2026-02-05T07:02:14.98Z" }, + { url = "https://files.pythonhosted.org/packages/e9/a5/1be1516390333ff9be3a9cb648c9f33df79d5096e5884b5df71a588af463/opencv_python-4.13.0.92-cp37-abi3-win_amd64.whl", hash = "sha256:423d934c9fafb91aad38edf26efb46da91ffbc05f3f59c4b0c72e699720706f5", size = 40212062, upload-time = "2026-02-05T07:02:12.724Z" }, +] + +[[package]] +name = "requests" +version = "2.32.5" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "certifi" }, + { name = "charset-normalizer" }, + { name = "idna" }, + { name = "urllib3" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/c9/74/b3ff8e6c8446842c3f5c837e9c3dfcfe2018ea6ecef224c710c85ef728f4/requests-2.32.5.tar.gz", hash = "sha256:dbba0bac56e100853db0ea71b82b4dfd5fe2bf6d3754a8893c3af500cec7d7cf", size = 134517, upload-time = "2025-08-18T20:46:02.573Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/1e/db/4254e3eabe8020b458f1a747140d32277ec7a271daf1d235b70dc0b4e6e3/requests-2.32.5-py3-none-any.whl", hash = "sha256:2462f94637a34fd532264295e186976db0f5d453d1cdd31473c85a6a161affb6", size = 64738, upload-time = "2025-08-18T20:46:00.542Z" }, +] + +[[package]] +name = "urllib3" +version = "2.6.3" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/c7/24/5f1b3bdffd70275f6661c76461e25f024d5a38a46f04aaca912426a2b1d3/urllib3-2.6.3.tar.gz", hash = "sha256:1b62b6884944a57dbe321509ab94fd4d3b307075e0c2eae991ac71ee15ad38ed", size = 435556, upload-time = "2026-01-07T16:24:43.925Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/39/08/aaaad47bc4e9dc8c725e68f9d04865dbcb2052843ff09c97b08904852d84/urllib3-2.6.3-py3-none-any.whl", hash = "sha256:bf272323e553dfb2e87d9bfd225ca7b0f467b919d7bbd355436d3fd37cb0acd4", size = 131584, upload-time = "2026-01-07T16:24:42.685Z" }, +]