Update app.py

app.py

@@ -129,21 +129,8 @@ class ConversationBot:
         return state, state
 
     def run_image(self, image, state, txt, lang):
-        image_filename = os.path.join('image', f"{str(uuid.uuid4())[:8]}.png")
-        print("======>Auto Resize Image...")
-        img = Image.open(image.name)
-        width, height = img.size
-        ratio = min(512 / width, 512 / height)
-        width_new, height_new = (round(width * ratio), round(height * ratio))
-        width_new = int(np.round(width_new / 64.0)) * 64
-        height_new = int(np.round(height_new / 64.0)) * 64
-        img = img.resize((width_new, height_new))
-        img = img.convert('RGB')
-        img.save(image_filename, "PNG")
-        print(f"Resize image form {width}x{height} to {width_new}x{height_new}")
-        description = self.models['ImageCaptioning'].inference(image_filename)
         if lang == 'Chinese':
-            Human_prompt = f'\nHuman: 提供一张名为 {image_filename}的图片。它的描述是: {description}。 这些信息帮助你理解这个图像，但是你应该使用工具来完成下面的任务，而不是直接从我的描述中想象。 如果你明白了, 说 \"收到\". \n'
+            Human_prompt = f'\nHuman: 提供一张名为 123的图片。它的描述是: 一只猫和一只狗。 这些信息帮助你理解这个图像，但是你应该使用工具来完成下面的任务，而不是直接从我的描述中想象。 如果你明白了, 说 \"收到\". \n'
             AI_prompt = "收到。  "
         else:
             Human_prompt = f'\nHuman: provide a figure named {image_filename}. The description is: {description}. This information helps you to understand this image, but you should use tools to finish following tasks, rather than directly imagine from my description. If you understand, say \"Received\". \n'
@@ -176,9 +163,7 @@ class ConversationBot:
 
         return gr.update(visible = True)
 
-bot = ConversationBot({'Text2Image': 'cpu',
-                       'ImageCaptioning': 'cpu'
-                       })
+bot = ConversationBot({})
 
 with gr.Blocks(css="#chatbot {overflow:auto; height:500px;}") as demo:
     gr.Markdown("<h3><center>Visual ChatGPT</center></h3>")
@@ -234,7 +219,6 @@ with gr.Blocks(css="#chatbot {overflow:auto; height:500px;}") as demo:
     txt.submit(lambda: "", None, txt)
     run.click(bot.run_text, [txt, state], [chatbot, state])
     run.click(lambda: "", None, txt)
-    btn.upload(bot.run_image, [btn, state, txt, lang], [chatbot, state, txt])
     clear.click(bot.memory.clear)
     clear.click(lambda: [], None, chatbot)
     clear.click(lambda: [], None, state)