Update app.py

app.py

@@ -9,14 +9,15 @@ from ultralytics import YOLO
 # Remove extra CLI arguments (like "--import") from Spaces.
 sys.argv = [arg for arg in sys.argv if arg != "--import"]
 
-# Load the YOLO11-pose model (will auto-download if needed)
+# Load the YOLO11-pose model (auto-downloads if needed)
 model = YOLO("yolo11n-pose.pt")
 
 def process_input(uploaded_file, youtube_link, image_url):
     """
     Process an uploaded file, a YouTube link, or an image URL for pose detection.
-    Returns a tuple: (download_file_path, display_file_path, status_message).
-    Priority: YouTube link > Image URL > Uploaded file.
+    Priority is: YouTube link > Image URL > Uploaded file.
+    Returns a tuple:
+      (download_file_path, display_file_path, status_message)
     """
     input_path = None
 
@@ -58,48 +59,60 @@ def process_input(uploaded_file, youtube_link, image_url):
 
     output_path = None
     try:
-        # If the results object has a save_path attribute, use it.
+        # If the result has a save_path attribute, use it.
         if hasattr(results[0], "save_path"):
             output_path = results[0].save_path
         else:
-            # Otherwise, generate an annotated image using plot() and save it manually.
+            # Otherwise, use plot() to get an annotated image and save it.
             annotated = results[0].plot()  # returns a numpy array
             output_path = os.path.join(tempfile.gettempdir(), "annotated.jpg")
             cv2.imwrite(output_path, annotated)
     except Exception as e:
         return None, None, f"Error processing the file: {e}"
 
-    # Clean up the temporary input file if downloaded.
+    # Clean up temporary file if it was downloaded (from YouTube or Image URL)
     if (youtube_link or (image_url and image_url.strip())) and input_path and os.path.exists(input_path):
         os.remove(input_path)
     
-    # Return the same output path for both download and display.
     return output_path, output_path, "Success!"
 
 # Define the Gradio interface.
 with gr.Blocks() as demo:
-    gr.Markdown("# Pose Detection with YOLO11-pose")
-    gr.Image(value="crowdresult.jpg", label="Crowd Result", interactive=False)
-    gr.Markdown("Upload an image/video, provide an image URL, or supply a YouTube link to detect human poses.")
-    
-    with gr.Row():
-        file_input = gr.File(label="Upload Image/Video")
-    with gr.Row():
-        youtube_input = gr.Textbox(label="YouTube Link", placeholder="https://...")
-        image_url_input = gr.Textbox(label="Image URL", placeholder="https://...")
-    
-    # Three outputs: one for file download, one for immediate display, and one for status text.
+    # Header image scaled down to 25% using HTML.
+    gr.HTML("<div style='text-align: center;'><img src='crowdresult.jpg' style='width:25%;'></div>")
+    gr.Markdown("## Pose Detection with YOLO11-pose")
+    gr.Markdown("Choose one of the input methods below. The pose detection will run automatically when you provide an input, and the annotated result will be displayed below.")
+
+    # Prepare output components (they will display the annotated result and a download link)
     output_file = gr.File(label="Download Annotated Output")
     output_display = gr.Image(label="Annotated Output")
     output_text = gr.Textbox(label="Status", interactive=False)
-    run_button = gr.Button("Run Pose Detection")
-    
-    run_button.click(
-        process_input,
-        inputs=[file_input, youtube_input, image_url_input],
-        outputs=[output_file, output_display, output_text]
-    )
 
-# Only launch the interface if executed directly.
+    # Create three tabs for the different input methods.
+    with gr.Tabs():
+        with gr.TabItem("Upload File"):
+            file_input = gr.File(label="Upload Image/Video")
+            # Automatically run detection when a file is uploaded.
+            file_input.change(
+                fn=process_input, 
+                inputs=[file_input, gr.State(None), gr.State(None)],
+                outputs=[output_file, output_display, output_text]
+            )
+        with gr.TabItem("YouTube Link"):
+            youtube_input = gr.Textbox(label="YouTube Link", placeholder="https://...")
+            youtube_input.change(
+                fn=process_input, 
+                inputs=[gr.State(None), youtube_input, gr.State(None)],
+                outputs=[output_file, output_display, output_text]
+            )
+        with gr.TabItem("Image URL"):
+            image_url_input = gr.Textbox(label="Image URL", placeholder="https://...")
+            image_url_input.change(
+                fn=process_input, 
+                inputs=[gr.State(None), gr.State(None), image_url_input],
+                outputs=[output_file, output_display, output_text]
+            )
+
+# Only launch the interface if the script is executed directly.
 if __name__ == "__main__":
     demo.launch()