Add embedding model selection and comparison test scripts

- Update DetectLogosDETR to support both CLIP and DINOv2 models
  - Rename clip_model parameter to embedding_model
  - Add model type detection for different embedding extraction
  - DINOv2 uses CLS token, CLIP uses get_image_features()
- Add -e/--embedding-model argument to test_logo_detection.py
- Include model name in file output header
- Add run_threshold_tests.sh for testing various threshold/margin values
- Add run_model_comparison.sh for comparing CLIP vs DINOv2 models
This commit is contained in:
Rick McEwen
2026-01-02 12:05:27 -05:00
parent a3008ee57f
commit 94db5bd40b
4 changed files with 312 additions and 30 deletions

141
run_threshold_tests.sh Executable file
View File

@ -0,0 +1,141 @@
#!/bin/bash
#
# Run logo detection tests with various threshold and margin settings.
# Uses multi-ref (max) matching method for all tests.
#
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
OUTPUT_FILE="${SCRIPT_DIR}/threshold_test_results.txt"
# Common parameters
NUM_LOGOS=20
REFS_PER_LOGO=10
POSITIVE_SAMPLES=20
NEGATIVE_SAMPLES=100
MIN_MATCHING_REFS=3
SEED=42
# Clear output file and write header
echo "Threshold Optimization Tests" > "$OUTPUT_FILE"
echo "=============================" >> "$OUTPUT_FILE"
echo "Date: $(date)" >> "$OUTPUT_FILE"
echo "" >> "$OUTPUT_FILE"
echo "Common Parameters:" >> "$OUTPUT_FILE"
echo " Matching method: multi-ref (max)" >> "$OUTPUT_FILE"
echo " Reference logos: $NUM_LOGOS" >> "$OUTPUT_FILE"
echo " Refs per logo: $REFS_PER_LOGO" >> "$OUTPUT_FILE"
echo " Positive samples: $POSITIVE_SAMPLES" >> "$OUTPUT_FILE"
echo " Negative samples: $NEGATIVE_SAMPLES" >> "$OUTPUT_FILE"
echo " Min matching refs: $MIN_MATCHING_REFS" >> "$OUTPUT_FILE"
echo " Seed: $SEED" >> "$OUTPUT_FILE"
echo "" >> "$OUTPUT_FILE"
echo "Running threshold optimization tests..."
echo " Matching method: multi-ref (max)"
echo " Reference logos: $NUM_LOGOS"
echo " Refs per logo: $REFS_PER_LOGO"
echo " Seed: $SEED"
echo ""
# Test 1: Default parameters (baseline)
echo "=== Test 1: Default parameters (threshold=0.70, margin=0.05) ==="
uv run python "$SCRIPT_DIR/test_logo_detection.py" \
--num-logos $NUM_LOGOS \
--refs-per-logo $REFS_PER_LOGO \
--positive-samples $POSITIVE_SAMPLES \
--negative-samples $NEGATIVE_SAMPLES \
--matching-method multi-ref \
--min-matching-refs $MIN_MATCHING_REFS \
--use-max-similarity \
--threshold 0.70 \
--margin 0.05 \
--seed $SEED \
--output-file "$OUTPUT_FILE"
echo ""
# Test 2: Higher threshold
echo "=== Test 2: Higher threshold (threshold=0.80, margin=0.05) ==="
uv run python "$SCRIPT_DIR/test_logo_detection.py" \
--num-logos $NUM_LOGOS \
--refs-per-logo $REFS_PER_LOGO \
--positive-samples $POSITIVE_SAMPLES \
--negative-samples $NEGATIVE_SAMPLES \
--matching-method multi-ref \
--min-matching-refs $MIN_MATCHING_REFS \
--use-max-similarity \
--threshold 0.80 \
--margin 0.05 \
--seed $SEED \
--output-file "$OUTPUT_FILE"
echo ""
# Test 3: Higher threshold + larger margin
echo "=== Test 3: Higher threshold + larger margin (threshold=0.80, margin=0.10) ==="
uv run python "$SCRIPT_DIR/test_logo_detection.py" \
--num-logos $NUM_LOGOS \
--refs-per-logo $REFS_PER_LOGO \
--positive-samples $POSITIVE_SAMPLES \
--negative-samples $NEGATIVE_SAMPLES \
--matching-method multi-ref \
--min-matching-refs $MIN_MATCHING_REFS \
--use-max-similarity \
--threshold 0.80 \
--margin 0.10 \
--seed $SEED \
--output-file "$OUTPUT_FILE"
echo ""
# Test 4: Very high threshold
echo "=== Test 4: Very high threshold (threshold=0.85, margin=0.10) ==="
uv run python "$SCRIPT_DIR/test_logo_detection.py" \
--num-logos $NUM_LOGOS \
--refs-per-logo $REFS_PER_LOGO \
--positive-samples $POSITIVE_SAMPLES \
--negative-samples $NEGATIVE_SAMPLES \
--matching-method multi-ref \
--min-matching-refs $MIN_MATCHING_REFS \
--use-max-similarity \
--threshold 0.85 \
--margin 0.10 \
--seed $SEED \
--output-file "$OUTPUT_FILE"
echo ""
# Test 5: Very high threshold + large margin
echo "=== Test 5: Strict parameters (threshold=0.85, margin=0.15) ==="
uv run python "$SCRIPT_DIR/test_logo_detection.py" \
--num-logos $NUM_LOGOS \
--refs-per-logo $REFS_PER_LOGO \
--positive-samples $POSITIVE_SAMPLES \
--negative-samples $NEGATIVE_SAMPLES \
--matching-method multi-ref \
--min-matching-refs $MIN_MATCHING_REFS \
--use-max-similarity \
--threshold 0.85 \
--margin 0.15 \
--seed $SEED \
--output-file "$OUTPUT_FILE"
echo ""
# Test 6: Maximum strictness
echo "=== Test 6: Maximum strictness (threshold=0.90, margin=0.15) ==="
uv run python "$SCRIPT_DIR/test_logo_detection.py" \
--num-logos $NUM_LOGOS \
--refs-per-logo $REFS_PER_LOGO \
--positive-samples $POSITIVE_SAMPLES \
--negative-samples $NEGATIVE_SAMPLES \
--matching-method multi-ref \
--min-matching-refs $MIN_MATCHING_REFS \
--use-max-similarity \
--threshold 0.90 \
--margin 0.15 \
--seed $SEED \
--output-file "$OUTPUT_FILE"
echo ""
echo "Results saved to: $OUTPUT_FILE"