#!/bin/bash # # Test different numbers of reference logos per brand to find optimal setting. # Uses baseline CLIP with multi-ref (max) matching method. # # Usage: # ./run_refs_per_logo_test.sh # SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" OUTPUT_FILE="${SCRIPT_DIR}/test_results/refs_per_logo_analysis.txt" # Model - baseline CLIP (best for unknown logos) MODEL="openai/clip-vit-large-patch14" # Fixed parameters NUM_LOGOS=20 POSITIVE_SAMPLES=20 NEGATIVE_SAMPLES=100 MIN_MATCHING_REFS=1 THRESHOLD=0.70 MARGIN=0.05 SEED=42 # Refs per logo values to test REFS_TO_TEST="1 2 3 5 7 10 15 20" # Create output directory if needed mkdir -p "${SCRIPT_DIR}/test_results" # Clear output file and write header cat > "$OUTPUT_FILE" << EOF Reference Logos Per Brand Optimization ====================================== Date: $(date) Model: ${MODEL} Method: multi-ref (max) Fixed Parameters: Number of logo brands: ${NUM_LOGOS} Similarity threshold: ${THRESHOLD} Margin: ${MARGIN} Min matching refs: ${MIN_MATCHING_REFS} Positive samples/logo: ${POSITIVE_SAMPLES} Negative samples/logo: ${NEGATIVE_SAMPLES} Seed: ${SEED} Testing refs per logo: ${REFS_TO_TEST} EOF echo "Reference Logos Per Brand Optimization" echo "=======================================" echo "Model: ${MODEL}" echo "Testing refs per logo: ${REFS_TO_TEST}" echo "" # Results table header echo "Results Summary:" >> "$OUTPUT_FILE" echo "----------------" >> "$OUTPUT_FILE" printf "%-12s %8s %8s %8s %8s %8s %8s\n" "Refs/Logo" "TP" "FP" "FN" "Prec" "Recall" "F1" >> "$OUTPUT_FILE" echo "------------------------------------------------------------------------" >> "$OUTPUT_FILE" # Track best result BEST_F1=0 BEST_REFS=0 for REFS in ${REFS_TO_TEST}; do echo "=== Testing refs_per_logo=${REFS} ===" # Run test and capture output OUTPUT=$(uv run python "$SCRIPT_DIR/test_logo_detection.py" \ --num-logos $NUM_LOGOS \ --refs-per-logo $REFS \ --positive-samples $POSITIVE_SAMPLES \ --negative-samples $NEGATIVE_SAMPLES \ --matching-method multi-ref \ --min-matching-refs $MIN_MATCHING_REFS \ --use-max-similarity \ --threshold $THRESHOLD \ --margin $MARGIN \ --seed $SEED \ --embedding-model "$MODEL" \ 2>&1) # Extract metrics TP=$(echo "${OUTPUT}" | grep "True Positives" | grep -oE "[0-9]+" | head -1) FP=$(echo "${OUTPUT}" | grep "False Positives" | grep -oE "[0-9]+" | head -1) FN=$(echo "${OUTPUT}" | grep "False Negatives" | grep -oE "[0-9]+" | head -1) PREC=$(echo "${OUTPUT}" | grep "Precision:" | grep -oE "[0-9]+\.[0-9]+%" | head -1) RECALL=$(echo "${OUTPUT}" | grep "Recall:" | grep -oE "[0-9]+\.[0-9]+%" | head -1) F1=$(echo "${OUTPUT}" | grep "F1 Score:" | grep -oE "[0-9]+\.[0-9]+%" | head -1) # Print to console echo " TP: ${TP}, FP: ${FP}, FN: ${FN}" echo " Precision: ${PREC}, Recall: ${RECALL}, F1: ${F1}" echo "" # Add to results table printf "%-12s %8s %8s %8s %8s %8s %8s\n" "${REFS}" "${TP}" "${FP}" "${FN}" "${PREC}" "${RECALL}" "${F1}" >> "$OUTPUT_FILE" # Track best F1 F1_NUM=$(echo "${F1}" | tr -d '%') if [ -n "$F1_NUM" ]; then BETTER=$(echo "${F1_NUM} > ${BEST_F1}" | bc -l 2>/dev/null || echo "0") if [ "$BETTER" = "1" ]; then BEST_F1="${F1_NUM}" BEST_REFS="${REFS}" fi fi # Also append full output for this test echo "" >> "$OUTPUT_FILE" echo "======================================================================" >> "$OUTPUT_FILE" echo "DETAILED RESULTS: refs_per_logo=${REFS}" >> "$OUTPUT_FILE" echo "======================================================================" >> "$OUTPUT_FILE" echo "${OUTPUT}" | grep -A 50 "Configuration:" | head -30 >> "$OUTPUT_FILE" echo "" >> "$OUTPUT_FILE" done # Summary echo "------------------------------------------------------------------------" >> "$OUTPUT_FILE" echo "" >> "$OUTPUT_FILE" echo "OPTIMAL SETTING: refs_per_logo=${BEST_REFS} (F1 = ${BEST_F1}%)" >> "$OUTPUT_FILE" echo "" >> "$OUTPUT_FILE" echo "=======================================" echo "OPTIMAL: refs_per_logo=${BEST_REFS} (F1 = ${BEST_F1}%)" echo "=======================================" echo "" echo "Results saved to: $OUTPUT_FILE"