Update app.py

app.py

@@ -114,15 +114,14 @@ tokenizer = CLIPTokenizer.from_pretrained("Diangle/clip4clip-webvid")
 def search(search_sentence):
     inputs = tokenizer(text=search_sentence , return_tensors="pt", padding=True)
 
-    outputs = model(input_ids=inputs["input_ids"], attention_mask=inputs["attention_mask"], return_dict=False)  
-    text_projection = model.state_dict()['text_projection.weight']
-    text_embeds = outputs[1] @ text_projection
-    final_output = text_embeds[torch.arange(text_embeds.shape[0]), inputs["input_ids"].argmax(dim=-1)]
+    outputs = model(input_ids=inputs["input_ids"], attention_mask=inputs["attention_mask"])  
+    # text_projection = model.state_dict()['text_projection.weight']
+    # text_embeds = outputs[1] @ text_projection
+    # final_output = text_embeds[torch.arange(text_embeds.shape[0]), inputs["input_ids"].argmax(dim=-1)]
 
     # Normalization
-    final_output = final_output / final_output.norm(dim=-1, keepdim=True)
-    final_output = final_output.cpu().detach().numpy()
-    sequence_output = final_output / np.sum(final_output**2, axis=1, keepdims=True)
+    final_output = outputs[1] / outputs[1].norm(dim=-1, keepdim=True)
+    sequence_output = final_output.cpu().detach().numpy()
     
     nn_search = NearestNeighbors(n_neighbors=5, metric='binary', rerank_from=100)
     nn_search.fit(np.packbits((ft_visual_features_database > 0.0).astype(bool), axis=1), o_data=ft_visual_features_database)