added prefix for IC

app.py

@@ -243,6 +243,8 @@ def inference(img, text, is_translate):
     text = clip.tokenize([text]).to(device)
     with torch.no_grad():
       prefix = clip_model.encode_text(text).to(device, dtype=torch.float32)
+      prefix_embed = model.clip_project(prefix).reshape(1, prefix_length, -1)
+      generated_text_prefix = generate_beam(model, tokenizer, embed=prefix_embed)[0]
 
   else:
     if img is None:
@@ -253,13 +255,9 @@ def inference(img, text, is_translate):
 
     with torch.no_grad():
       prefix = clip_model.encode_image(image).to(device, dtype=torch.float32)
+      prefix_embed = model.clip_project(prefix).reshape(1, prefix_length, -1)
+      generated_text_prefix = generate_beam(model, tokenizer, embed=prefix_embed, prompt="Một bức ảnh về")[0]
 
-  prefix_embed = model.clip_project(prefix).reshape(1, prefix_length, -1)
-
-  if use_beam_search:
-    generated_text_prefix = generate_beam(model, tokenizer, embed=prefix_embed)[0]
-  else:
-    generated_text_prefix = generate2(model, tokenizer, embed=prefix_embed)
   return generated_text_prefix
   
 title = "CLIP Dual encoder"