Update app.py

app.py

@@ -112,15 +112,11 @@ model = CLIPTextModelWithProjection.from_pretrained("Diangle/clip4clip-webvid")
 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"])  
-    # 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 = outputs[1] / outputs[1].norm(dim=-1, keepdim=True)
+    inputs = tokenizer(text=search_sentence , return_tensors="pt")
+    outputs = model(input_ids=inputs["input_ids"], attention_mask=inputs["attention_mask"])
+    
+    # Normalizing the embeddings:
+    final_output = outputs[0] / outputs[0].norm(dim=-1, keepdim=True)
     sequence_output = final_output.cpu().detach().numpy()
     
     nn_search = NearestNeighbors(n_neighbors=5, metric='binary', rerank_from=100)