output

main.py

@@ -187,24 +187,26 @@ def run_UI():
                         video_output1 = gr.PlayableVideo(height=512,  label = "Estimate human 2d poses", show_label=True)
                         video_output2 = gr.PlayableVideo(height=512,  label = "Estimate human 3d poses", show_label=True)
                         video_output3 = gr.PlayableVideo(height=512,  label = "Estimate human hand poses", show_label=True)
-                        video_output4 = gr.Video(height=512)
+                        video_output4 = gr.Video(height=512, label = "Detection and tracking", show_label=True, format="mp4")
 
             with gr.Tab("Record video with webcam"):
-                with gr.Row():
-                    with gr.Column():
-                        webcam_input = gr.Video(source="webcam", height=612)
-                        
-                        web_kpthr = gr.Slider(minimum=1e3, maximum=1e6, step=1e3, default=1e3, label='Keypoint threshold')
-
-                        submit_pose_web = gr.Button("Make 2d pose estimation")
-                        submit_pose3d_web = gr.Button("Make 3d pose estimation")
-                        submit_hand_web = gr.Button("Make 2d hand estimation")
-                        submit_detect_web = gr.Button("Detect and track objects")
+                
+                with gr.Column:
+                    with gr.Row():
+                        with gr.Column():
+                            webcam_input = gr.Video(source="webcam", height=612)
+                            
+                            web_kpthr = gr.Slider(minimum=0.1, maximum=1, step=1e3, default=0.3, label='Keypoint threshold')
+
+                            submit_pose_web = gr.Button("Make 2d pose estimation")
+                            submit_pose3d_web = gr.Button("Make 3d pose estimation")
+                            submit_hand_web = gr.Button("Make 2d hand estimation")
+                            submit_detect_web = gr.Button("Detect and track objects")
 
                     webcam_output1 = gr.PlayableVideo(height=512,  label = "Estimate human 2d poses", show_label=True)
                     webcam_output2 = gr.PlayableVideo(height=512,  label = "Estimate human 3d poses", show_label=True)
                     webcam_output3 = gr.PlayableVideo(height=512,  label = "Estimate human hand position", show_label=True)
-                    webcam_output4 = gr.Video(height=512)
+                    webcam_output4 = gr.Video(height=512, label = "Detection and tracking", show_label=True, format="mp4")