remove img upload button

app.py

@@ -111,7 +111,7 @@ def gradio_reset(chat_state, img_list):
         img_list = []
     return None, gr.update(value=None, interactive=True), gr.update(value=None, interactive=True), gr.update(placeholder='Please upload your video first', interactive=False),gr.update(value="Upload & Start Chat", interactive=True), chat_state, img_list
 
-def upload_imgorvideo(gr_video, gr_img, text_input, chat_state,chatbot):
+'''def upload_imgorvideo(gr_video, gr_img, text_input, chat_state,chatbot):
     if args.model_type == 'vicuna':
         chat_state = default_conversation.copy()
     else:
@@ -134,7 +134,20 @@ def upload_imgorvideo(gr_video, gr_img, text_input, chat_state,chatbot):
         return gr.update(interactive=False), gr.update(interactive=False), gr.update(interactive=True, placeholder='Type and press Enter'), gr.update(value="Start Chatting", interactive=False), chat_state, img_list,chatbot
     else:
         # img_list = []
-        return gr.update(interactive=False), gr.update(interactive=False, placeholder='Currently, only one input is supported'), gr.update(value="Currently, only one input is supported", interactive=False), chat_state, None,chatbot
+        return gr.update(interactive=False), gr.update(interactive=False, placeholder='Currently, only one input is supported'), gr.update(value="Currently, only one input is supported", interactive=False), chat_state, None,chatbot'''
+
+def upload_imgorvideo(gr_video, text_input, chat_state, chatbot):
+    if args.model_type == 'vicuna':
+        chat_state = default_conversation.copy()
+    else:
+        chat_state = conv_llava_llama_2.copy()
+    
+    print(gr_video)
+    chatbot = chatbot + [((gr_video,), None)]
+    chat_state.system =  "You are able to understand the visual content that the user provides. Follow the instructions carefully and explain your answers in detail."
+    img_list = []
+    llm_message = chat.upload_video_without_audio(gr_video, chat_state, img_list)
+    return gr.update(interactive=False), gr.update(interactive=True, placeholder='Type and press Enter'), gr.update(value="Start Chatting", interactive=False), chat_state, img_list,chatbot
 
 def gradio_ask(user_message, chatbot, chat_state):
     if len(user_message) == 0:
@@ -239,8 +252,8 @@ with gr.Blocks() as demo:
         ], inputs=[video, text_input])'''
         
     gr.Markdown(cite_markdown)
-    #upload_button.click(upload_imgorvideo, [video, text_input, chat_state,chatbot], [video, text_input, upload_button, chat_state, img_list,chatbot])
-    upload_button.click(upload_imgorvideo, [video, image, text_input, chat_state,chatbot], [video, image, text_input, upload_button, chat_state, img_list,chatbot])
+    upload_button.click(upload_imgorvideo, [video, text_input, chat_state,chatbot], [video, text_input, upload_button, chat_state, img_list,chatbot])
+    #upload_button.click(upload_imgorvideo, [video, image, text_input, chat_state,chatbot], [video, image, text_input, upload_button, chat_state, img_list,chatbot])
 
     text_input.submit(gradio_ask, [text_input, chatbot, chat_state], [text_input, chatbot, chat_state]).then(
         gradio_answer, [chatbot, chat_state, img_list, num_beams, temperature], [chatbot, chat_state, img_list]

eval_configs/conversation_demo.yaml

@@ -16,7 +16,7 @@ model:
   imagebind_ckpt_path: "ckpt/imagebind_path/"
 
   # The ckpt of vision branch after stage1 pretrained, 
-  ckpt: 'ckpt/VL_LLaMA_2_7B_Finetuned.pth'   # you can use our pretrained ckpt from https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-2-13B-Pretrained/
+  ckpt: 'ckpt/VL_LLaMA_2_7B_Finetuned.pth'  # you can use our pretrained ckpt from https://huggingface.co/DAMO-NLP-SG/Video-LLaMA-2-13B-Pretrained/
 
 
   # only train vision branch