Update app.py

app.py

@@ -4,30 +4,123 @@ import os
 
 BACKEND_URL = os.environ.get("BACKEND_URL", "").strip()
 
-if BACKEND_URL:
+# Create persistent client
+try:
+    client = Client(BACKEND_URL, headers={"ngrok-skip-browser-warning": "true"})
+    backend_available = True
+except:
+    client = None
+    backend_available = False
+
+def forward_to_backend(fn_name, *args):
+    """Generic function to forward any call to backend"""
+    if not client:
+        return [gr.update() for _ in range(7)]
     try:
-        # Load the entire interface from backend
-        demo = gr.Interface.load(
-            name=BACKEND_URL,
-            title="PrimateFace Detection, Pose & Gaze Demo",
-            description="Connected to GPU backend server"
-        )
-        # Add header to bypass ngrok warning
-        demo.headers = {"ngrok-skip-browser-warning": "true"}
+        return client.predict(*args, api_name=fn_name)
     except Exception as e:
-        # Fallback if backend is down
-        demo = gr.Interface(
-            fn=lambda x: "GPU server is offline. Please try again later.",
-            inputs=gr.Textbox(),
-            outputs=gr.Textbox(),
-            title="PrimateFace Demo - Offline"
+        print(f"Error calling {fn_name}: {e}")
+        return [gr.update() for _ in range(7)]
+
+# Wrapper functions
+def handle_file_upload_preview(file_obj):
+    return forward_to_backend("/handle_file_upload_preview", file_obj)
+
+def handle_webcam_capture(snapshot):
+    return forward_to_backend("/handle_webcam_capture", snapshot)
+
+def process_media(file_obj, webcam_img, model_type, conf_thresh, max_dets, task_type):
+    return forward_to_backend("/process_media", file_obj, webcam_img, model_type, conf_thresh, max_dets, task_type)
+
+def clear_all_media_and_outputs():
+    return forward_to_backend("/clear_all_media_and_outputs")
+
+def handle_example_select(evt: gr.SelectData):
+    """Handle example selection locally and update input_file"""
+    # Extract the image path from the dataset
+    if isinstance(evt.value, dict) and 'image' in evt.value:
+        return evt.value['image']
+    return None
+
+# Build the interface
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("<center><h1>PrimateFace Detection, Pose Estimation, and Gaze Estimation Demo</h1></center>")
+    
+    if not backend_available:
+        gr.Markdown("### 🔴 GPU Server Offline - Please check back later")
+    else:
+        gr.Markdown("Upload an image/video or use your webcam. For webcam, press 'Enter' to take a snapshot.")
+        gr.Markdown("Click 'Detect Faces' for results.")
+        
+        with gr.Row():
+            with gr.Column(scale=1):
+                with gr.Tabs():
+                    with gr.TabItem("Upload File"):
+                        input_file = gr.File(label="Upload Image or Video Here", file_types=["image", ".mp4", ".avi", ".mov", ".mkv", ".webm", ".gif"])
+                        display_raw_image_file = gr.Image(label="Raw Image Preview", type="pil", interactive=False, visible=False)
+                        display_raw_video_file = gr.Video(label="Raw Video Preview", interactive=False, visible=False)
+                    
+                    with gr.TabItem("Webcam"):
+                        gr.Markdown("**Using the Webcam:** Click on feed or press Enter to capture")
+                        input_webcam = gr.Image(sources=["webcam"], type="pil", label="Live Webcam")
+                        display_raw_image_webcam = gr.Image(label="Captured Snapshot Preview", type="pil", interactive=False, visible=False)
+                
+                clear_all_button = gr.Button("Clear All Inputs & Outputs")
+            
+            with gr.Column(scale=1):
+                gr.Markdown("### Processed Output")
+                display_processed_image = gr.Image(label="Processed Image", type="pil", interactive=False, visible=False)
+                display_processed_video = gr.Video(label="Processed Video", interactive=False, visible=False)
+        
+        # Example images - host them on HF Space
+        example_paths = [
+            "images/allocebus_000003.jpeg",
+            "images/tarsius_000120.jpeg", 
+            "images/nasalis_proboscis-monkey.png",
+            "images/macaca_000032.jpeg",
+            "images/mandrillus_000011.jpeg",
+            "images/pongo_000006.jpeg"
+        ]
+        
+        example_dataset = gr.Dataset(
+            components=["image"],
+            samples=[[path] for path in example_paths],
+            label="Example Images (Click to use)",
+            samples_per_page=6
+        )
+        
+        submit_button = gr.Button("Detect Faces", variant="primary", scale=2)
+        
+        with gr.Column():
+            gr.Markdown("### Detection Controls")
+            model_choice_radio = gr.Radio(choices=["MMDetection"], value="MMDetection", label="Inferencer", visible=False)
+            task_type_dropdown = gr.Dropdown(
+                choices=["Face Detection", "Face Pose Estimation", "Gaze Estimation [experimental]"],
+                value="Face Detection",
+                label="Select Task"
+            )
+            conf_slider = gr.Slider(minimum=0.05, maximum=0.95, value=0.25, step=0.05, label="Confidence Threshold")
+            max_det_slider = gr.Slider(minimum=1, maximum=10, value=3, step=1, label="Max Detections")
+        
+        # Define outputs
+        file_preview_outputs = [display_raw_image_file, display_raw_video_file, input_file, display_processed_image, display_processed_video]
+        webcam_outputs = [display_raw_image_webcam, input_webcam, display_processed_image, display_processed_video]
+        process_outputs = [display_raw_image_file, display_raw_video_file, display_raw_image_webcam, display_processed_image, display_processed_video]
+        clear_outputs = [input_file, input_webcam, display_raw_image_file, display_raw_video_file, display_raw_image_webcam, display_processed_image, display_processed_video]
+        
+        # Wire events
+        input_file.change(handle_file_upload_preview, inputs=[input_file], outputs=file_preview_outputs)
+        input_webcam.change(handle_webcam_capture, inputs=[input_webcam], outputs=webcam_outputs)
+        
+        # Handle example selection
+        example_dataset.select(handle_example_select, outputs=[input_file])
+        
+        submit_button.click(
+            process_media,
+            inputs=[input_file, display_raw_image_webcam, model_choice_radio, conf_slider, max_det_slider, task_type_dropdown],
+            outputs=process_outputs
         )
-else:
-    demo = gr.Interface(
-        fn=lambda x: "Backend URL not configured in Space settings.",
-        inputs=gr.Textbox(),
-        outputs=gr.Textbox(),
-        title="PrimateFace Demo - Not Configured"
-    )
+        
+        clear_all_button.click(clear_all_media_and_outputs, outputs=clear_outputs)
 
 demo.launch()