app.py

app.py

@@ -37,12 +37,12 @@ def show_output_image(matched_images) :
    return image
    
 # Encode and normalize the search query using CLIP
-def encode_search_query(search_query, model):
+def encode_search_query(search_query, model, device):
     with torch.no_grad():
         inputs = tokenizer([search_query],  padding=True, return_tensors="pt")
         #inputs = processor(text=[search_query], images=None, return_tensors="pt", padding=True)
     text_features =  model.get_text_features(**inputs).detach().numpy()
-    return text_features
+    return np.array(text_features)
         
 # Find all matched photos
 def find_matches(text_features, photo_features, photo_ids, results_count=4):
@@ -62,7 +62,7 @@ def image_search(search_text, search_image, option):
   
   if option == "Text-To-Image" :
     # Extracting text features
-    text_features = encode_search_query(search_text, model)
+    text_features = encode_search_query(search_text, model, device)
   
     # Find the matched Images
     matched_images = find_matches(text_features, photo_features, photo_ids, 4)