app.py

app.py

@@ -52,7 +52,9 @@ def encode_search_query(search_query, model, device):
         #text_encoded = model.encode_text(clip.tokenize(search_query).to(device))
         #text_encoded /= text_encoded.norm(dim=-1, keepdim=True)
         # Retrieve the feature vector from the GPU and convert it to a numpy array
-    return model.get_text_features(**inputs).cpu().numpy()
+    text_features = model.get_text_features(**inputs).detach().numpy()
+    #text_features = model.get_text_features(**inputs).cpu().numpy()
+    return text_features
         #return text_encoded.cpu().numpy()
         
 # Find all matched photos
@@ -91,7 +93,8 @@ def image_search(search_text, search_image, option):
          processed_image = processor(text=None, images=search_image, return_tensors="pt", padding=True)["pixel_values"]
          image_feature = model.get_image_features(processed_image.to(device))
          image_feature /= image_feature.norm(dim=-1, keepdim=True)
-         image_feature = image_feature.cpu().numpy()
+      #image_feature = image_feature.cpu().numpy()
+      image_feature = image_feature.detach().numpy()
       # Find the matched Images
       matched_images = find_matches(image_feature, photo_features, photo_ids, 4)
       #is_input_image = True