Update New_file.txt

New_file.txt

@@ -49,8 +49,6 @@ similarities = cosine_similarity(ideal_embeddings, candidate_embeddings)
 print(similarities)
 
 
-## SWIN code
-
 import torch
 from transformers import SwinTransformer, SwinTransformerImageProcessor
 import torchvision.transforms as transforms
@@ -78,36 +76,35 @@ def preprocess_image(image_path):
 ideal_image_paths = ["ideal_image1.jpg", "ideal_image2.jpg", "ideal_image3.jpg"]  # Replace with your ideal image file paths
 candidate_image_paths = ["candidate_image1.jpg", "candidate_image2.jpg", "candidate_image3.jpg"]  # Replace with your candidate image file paths
 
-# Calculate embeddings for ideal images
-ideal_embeddings = []
-for image_path in ideal_image_paths:
-    inputs = preprocess_image(image_path)
-    with torch.no_grad():
-        output = model(**inputs)
-        embedding = output['pixel_values'][0].cpu().numpy()
-        ideal_embeddings.append(embedding)
+# Calculate cosine similarities between ideal and candidate images
+similarities = []
 
-# Calculate embeddings for candidate images
-candidate_embeddings = []
-for image_path in candidate_image_paths:
-    inputs = preprocess_image(image_path)
+for ideal_path in ideal_image_paths:
+    ideal_embedding = None
+    inputs_ideal = preprocess_image(ideal_path)
     with torch.no_grad():
-        output = model(**inputs)
-        embedding = output['pixel_values'][0].cpu().numpy()
-        candidate_embeddings.append(embedding)
-
-# Calculate cosine similarities between ideal and candidate images
-similarities = cosine_similarity(ideal_embeddings, candidate_embeddings)
+        output_ideal = model(**inputs_ideal)
+        ideal_embedding = output_ideal['pixel_values'][0].cpu().numpy()
+    
+    for candidate_path in candidate_image_paths:
+        candidate_embedding = None
+        inputs_candidate = preprocess_image(candidate_path)
+        with torch.no_grad():
+            output_candidate = model(**inputs_candidate)
+            candidate_embedding = output_candidate['pixel_values'][0].cpu().numpy()
+        
+        # Calculate cosine similarity between ideal and candidate embeddings
+        similarity = cosine_similarity([ideal_embedding], [candidate_embedding])[0][0]
+        similarities.append((ideal_path, candidate_path, similarity))
 
 # Set a similarity threshold (e.g., 0.7)
 threshold = 0.7
 
 # Find similar image pairs based on the threshold
 similar_pairs = []
-for i in range(len(ideal_image_paths)):
-    for j in range(len(candidate_image_paths)):
-        if similarities[i, j] > threshold:
-            similar_pairs.append((ideal_image_paths[i], candidate_image_paths[j]))
+for ideal_path, candidate_path, similarity in similarities:
+    if similarity > threshold:
+        similar_pairs.append((ideal_path, candidate_path))
 
 # Print similar image pairs
 for pair in similar_pairs: