update

app.py

@@ -1,63 +1,46 @@
+import os
 import gradio as gr
+from PIL import Image
 from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+respond = "hello!"
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
 
+def load_image(file_path):
+    """Load an image from a file and return it in a format suitable for Gradio."""
+    return Image.open(file_path)
+
+# Placeholder function to display initial images
+def initial_display(description):
+    query_image_path = os.path.join("images", "true1.jpg")
+    candidate_image_1_path = os.path.join("images", "false_1.jpg")
+    candidate_image_2_path = os.path.join("images", "true_2.jpg")
+    
+    query_image = load_image(query_image_path)
+    candidate_image_1 = load_image(candidate_image_1_path)
+    candidate_image_2 = load_image(candidate_image_2_path)
+    return query_image, candidate_image_1, candidate_image_2, "Initial setup complete. Click on the correct candidate image."
+
+
+with gr.Blocks as demo:
+    text_input = gr.Textbox(label="Enter description")
+    text_submit = gr.Button("Submit")
+    select_dataset = gr.Dropdown(choices=["hmdb","ocl"],value="ocl",label="select dataset"),
+    select_mode = gr.Dropdown(choices=["1","2","3","4"],value="1",label="select mode"),
+    
+    query_image = gr.Image(label="Query Image", type="file")
+    candidate_image_1 = gr.Image(label="Candidate Image 1", type="file")
+    candidate_image_2 = gr.Image(label="Candidate Image 2", type="file")
+    logs = gr.Textbox(label="Logs")
+    
+    text_submit.click(
+        initial_display,
+        inputs=text_input,
+        outputs=[query_image, candidate_image_1, candidate_image_2, logs]
+    )
 
 if __name__ == "__main__":
     demo.launch()

app1.py

@@ -0,0 +1,65 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+"""
+For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+"""
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+
+        response += token
+        yield response
+
+"""
+For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+"""
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Dropdown(choices=["hmdb","ocl"],value="ocl",label="select dataset"),
+        gr.Dropdown(choices=["1","2","3","4"],value="1",label="select mode"),
+        # gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        # gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        # gr.Slider(
+        #     minimum=0.1,
+        #     maximum=1.0,
+        #     value=0.95,
+        #     step=0.05,
+        #     label="Top-p (nucleus sampling)",
+        # ),
+    ],
+)
+
+
+if __name__ == "__main__":
+    demo.launch()