Update app.py

app.py

@@ -11,8 +11,8 @@ processor = ZhCLIPProcessor.from_pretrained(version)
 
 
 
-def get_result(image,text):
- inputs = processor(text=[text], images=image, return_tensors="pt", padding=True)
+def get_result(image,text,text1):
+ inputs = processor(text=[text,text1], images=image, return_tensors="pt", padding=True)
 
  outputs = model(**inputs)
  image_features = outputs.image_features
@@ -32,31 +32,18 @@ with gr.Blocks(
  image_input = gr.Image(type="pil",label="VQA Image Input")
  with gr.Row():
  with gr.Column(scale=1):
- chat_input = gr.Textbox(lines=1, label="VQA Question Input")
+ chat_input = gr.Textbox(lines=1, label="Captions0 Input")
+ chat_input1 = gr.Textbox(lines=1, label="Captions1 Input")
  with gr.Row():
  clear_button = gr.Button(value="Clear", interactive=True,width=30)
  submit_button = gr.Button(
  value="Submit", interactive=True, variant="primary"
  )
- '''
- cap_submit_button = gr.Button(
- value="Submit_CAP", interactive=True, variant="primary"
- )
- gpt3_submit_button = gr.Button(
- value="Submit_GPT3", interactive=True, variant="primary"
- )
- '''
+ 
  with gr.Column():
  caption_output = gr.Textbox(lines=0, label="ITM")
  
- chat_input.submit(
- get_result,
- [
- image_input,
- chat_input,
- ],
- [ caption_output],
- )
+ 
  clear_button.click(
  lambda: ("", [],"","",""),
  [],
@@ -68,6 +55,7 @@ with gr.Blocks(
  [
  image_input,
  chat_input,
+ chat_input1,
  ],
  [caption_output],
  )