Update main.py

main.py

@@ -49,27 +49,27 @@ def predict(item: Item):
     # all other images and returns a list with the pairs that have the highest 
     # cosine similarity score
     processed_images = util.paraphrase_mining_embeddings(encoded_image)
-    NUM_SIMILAR_IMAGES = 10 
+    #NUM_SIMILAR_IMAGES = 10 
     
     # =================
     # DUPLICATES
     # =================
-    print('Finding duplicate images...')
+    #print('Finding duplicate images...')
     # Filter list for duplicates. Results are triplets (score, image_id1, image_id2) and is scorted in decreasing order
     # A duplicate image will have a score of 1.00
     # It may be 0.9999 due to lossy image compression (.jpg)
-    duplicates = [image for image in processed_images if image[0] >= 0.999]
+    #duplicates = [image for image in processed_images if image[0] >= 0.999]
     
     # Output the top X duplicate images
-    for score, image_id1, image_id2 in duplicates[0:NUM_SIMILAR_IMAGES]:
-        print("\nScore: {:.3f}%".format(score * 100))
+    #for score, image_id1, image_id2 in duplicates[0:NUM_SIMILAR_IMAGES]:
+        #print("\nScore: {:.3f}%".format(score * 100))
 
     # Check if there are any duplicates
-    if duplicates:
+    #if duplicates:
         # Find the top score among duplicates
-        top_score = max(duplicates, key=lambda x: x[0])[0]
-        formatted_score = round(top_score * 100, 3)  # Multiplies by 100 and rounds to three decimal places
-        return ScoreResponse(score=formatted_score)        
+        #top_score = max(duplicates, key=lambda x: x[0])[0]
+        #formatted_score = round(top_score * 100, 3)  # Multiplies by 100 and rounds to three decimal places
+        #return ScoreResponse(score=formatted_score)        
     
     # =================
     # NEAR DUPLICATES
@@ -79,7 +79,7 @@ def predict(item: Item):
     # you will get larger clusters which have less similar images in it. Threshold 0 - 1.00
     # A threshold of 1.00 means the two images are exactly the same. Since we are finding near 
     # duplicate images, we can set it at 0.99 or any number 0 < X < 1.00.
-    threshold = 0.99
+    threshold = 1.0
     near_duplicates = [image for image in processed_images if image[0] < threshold]
     
     #for score, image_id1, image_id2 in near_duplicates[0:NUM_SIMILAR_IMAGES]: