Add --output-file option for clean results output

- Add --output-file argument to test_logo_detection.py that appends
  only the results summary (no progress indicators) to specified file
- Add write_results_to_file() with detailed header showing test type
  and method parameters
- Update run_comparison_tests.sh to use --output-file instead of
  tee/redirection, keeping console output separate from file output

run_comparison_tests.sh

@@ -16,10 +16,19 @@ MIN_MATCHING_REFS=3
 # Use a fixed seed for reproducibility across methods
 SEED=42
 
+# Clear output file and write header
 echo "Logo Detection Comparison Tests" > "$OUTPUT_FILE"
 echo "================================" >> "$OUTPUT_FILE"
 echo "Date: $(date)" >> "$OUTPUT_FILE"
 echo "" >> "$OUTPUT_FILE"
+echo "Common Parameters:" >> "$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 tests with:"
 echo "  Reference logos: $NUM_LOGOS"
@@ -31,7 +40,7 @@ echo "  Seed: $SEED"
 echo ""
 
 # Test 1: Simple matching (baseline - all matches above threshold)
-echo "=== Test 1: Simple matching (baseline) ===" | tee -a "$OUTPUT_FILE"
+echo "=== Test 1: Simple matching (baseline) ==="
 uv run python "$SCRIPT_DIR/test_logo_detection.py" \
     --num-logos $NUM_LOGOS \
     --refs-per-logo $REFS_PER_LOGO \
@@ -39,13 +48,12 @@ uv run python "$SCRIPT_DIR/test_logo_detection.py" \
     --negative-samples $NEGATIVE_SAMPLES \
     --matching-method simple \
     --seed $SEED \
-    2>&1 | tee -a "$OUTPUT_FILE"
+    --output-file "$OUTPUT_FILE"
 
-echo "" >> "$OUTPUT_FILE"
+echo ""
-echo "" >> "$OUTPUT_FILE"
 
 # Test 2: Margin-based matching
-echo "=== Test 2: Margin-based matching ===" | tee -a "$OUTPUT_FILE"
+echo "=== Test 2: Margin-based matching ==="
 uv run python "$SCRIPT_DIR/test_logo_detection.py" \
     --num-logos $NUM_LOGOS \
     --refs-per-logo $REFS_PER_LOGO \
@@ -53,13 +61,12 @@ uv run python "$SCRIPT_DIR/test_logo_detection.py" \
     --negative-samples $NEGATIVE_SAMPLES \
     --matching-method margin \
     --seed $SEED \
-    2>&1 | tee -a "$OUTPUT_FILE"
+    --output-file "$OUTPUT_FILE"
 
-echo "" >> "$OUTPUT_FILE"
+echo ""
-echo "" >> "$OUTPUT_FILE"
 
 # Test 3: Multi-ref with mean similarity
-echo "=== Test 3: Multi-ref matching (mean similarity) ===" | tee -a "$OUTPUT_FILE"
+echo "=== Test 3: Multi-ref matching (mean similarity) ==="
 uv run python "$SCRIPT_DIR/test_logo_detection.py" \
     --num-logos $NUM_LOGOS \
     --refs-per-logo $REFS_PER_LOGO \
@@ -68,13 +75,12 @@ uv run python "$SCRIPT_DIR/test_logo_detection.py" \
     --matching-method multi-ref \
     --min-matching-refs $MIN_MATCHING_REFS \
     --seed $SEED \
-    2>&1 | tee -a "$OUTPUT_FILE"
+    --output-file "$OUTPUT_FILE"
 
-echo "" >> "$OUTPUT_FILE"
+echo ""
-echo "" >> "$OUTPUT_FILE"
 
 # Test 4: Multi-ref with max similarity
-echo "=== Test 4: Multi-ref matching (max similarity) ===" | tee -a "$OUTPUT_FILE"
+echo "=== Test 4: Multi-ref matching (max similarity) ==="
 uv run python "$SCRIPT_DIR/test_logo_detection.py" \
     --num-logos $NUM_LOGOS \
     --refs-per-logo $REFS_PER_LOGO \
@@ -84,7 +90,7 @@ uv run python "$SCRIPT_DIR/test_logo_detection.py" \
     --min-matching-refs $MIN_MATCHING_REFS \
     --use-max-similarity \
     --seed $SEED \
-    2>&1 | tee -a "$OUTPUT_FILE"
+    --output-file "$OUTPUT_FILE"
 
 echo ""
 echo "Results saved to: $OUTPUT_FILE"

test_logo_detection.py

@@ -268,6 +268,12 @@ def main():
         action="store_true",
         help="Clear embedding cache before running",
     )
+    parser.add_argument(
+        "--output-file",
+        type=str,
+        default=None,
+        help="Append results summary to this file (no progress output, just results)",
+    )
 
     args = parser.parse_args()
     logger = setup_logging(args.verbose)
@@ -579,6 +585,92 @@ def main():
 
     print("=" * 60)
 
+    # Write results to file if requested
+    if args.output_file:
+        write_results_to_file(
+            output_path=Path(args.output_file),
+            args=args,
+            num_logos=len(sampled_logos),
+            total_refs=total_refs,
+            num_test_images=len(test_images),
+            true_positives=true_positives,
+            false_positives=false_positives,
+            false_negatives=false_negatives,
+            total_expected=total_expected,
+            precision=precision,
+            recall=recall,
+            f1=f1,
+        )
+        print(f"\nResults appended to: {args.output_file}")
+
+
+def write_results_to_file(
+    output_path: Path,
+    args,
+    num_logos: int,
+    total_refs: int,
+    num_test_images: int,
+    true_positives: int,
+    false_positives: int,
+    false_negatives: int,
+    total_expected: int,
+    precision: float,
+    recall: float,
+    f1: float,
+):
+    """Write results summary to file with detailed header."""
+    from datetime import datetime
+
+    # Build method description for header
+    if args.matching_method == "simple":
+        method_desc = "Simple (all matches above threshold)"
+    elif args.matching_method == "margin":
+        method_desc = f"Margin-based (margin={args.margin})"
+    else:  # multi-ref
+        agg = "max" if args.use_max_similarity else "mean"
+        method_desc = f"Multi-ref ({agg}, min_refs={args.min_matching_refs}, margin={args.margin})"
+
+    lines = [
+        "=" * 70,
+        f"TEST: {args.matching_method.upper()} MATCHING",
+        f"Method: {method_desc}",
+        "=" * 70,
+        f"Date: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}",
+        "",
+        "Configuration:",
+        f"  Reference logos:           {num_logos}",
+        f"  Refs per logo:             {args.refs_per_logo}",
+        f"  Total reference embeddings:{total_refs}",
+        f"  Positive samples/logo:     {args.positive_samples}",
+        f"  Negative samples/logo:     {args.negative_samples}",
+        f"  Test images processed:     {num_test_images}",
+        f"  CLIP threshold:            {args.threshold}",
+        f"  DETR threshold:            {args.detr_threshold}",
+    ]
+
+    if args.seed is not None:
+        lines.append(f"  Random seed:               {args.seed}")
+
+    lines.extend([
+        "",
+        "Results:",
+        f"  True Positives:   {true_positives:>6}",
+        f"  False Positives:  {false_positives:>6}",
+        f"  False Negatives:  {false_negatives:>6}",
+        f"  Total Expected:   {total_expected:>6}",
+        "",
+        "Scores:",
+        f"  Precision:  {precision:.4f} ({precision*100:.1f}%)",
+        f"  Recall:     {recall:.4f} ({recall*100:.1f}%)",
+        f"  F1 Score:   {f1:.4f} ({f1*100:.1f}%)",
+        "",
+        "",
+    ])
+
+    # Append to file
+    with open(output_path, "a") as f:
+        f.write("\n".join(lines))
+
 
 if __name__ == "__main__":
     main()