mp4 for tracking

main.py

@@ -63,9 +63,11 @@ def show_tracking(video_content, vis_out_dir, model):
         # Go through frames and write them 
         for frame_track in video_track:
             result_track = frame_track[0].plot()  # plot a BGR numpy array of predictions
+            out_track.write(result_track)
+        
         print("[INFO] Done with frames")
         #print(type(result_pose)) numpy ndarray
-        out_track.write(result_track)
+            
 
         out_track.release()
 
@@ -110,17 +112,17 @@ def infer(video, check):
         out_files.extend(out_file)
         print(out_files)
 
-    return out_files[0], out_files[1], out_files[2], out_file # out_files[3]
+    return "track.mp4", out_files[0], out_files[1], out_files[2] # out_files[3]
 
 def run():
     #https://github.com/open-mmlab/mmpose/blob/main/docs/en/user_guides/inference.md
-    check_web =  gr.CheckboxGroup(choices = ["Estimate human 2d poses", "Estimate human 2d hand poses", "Estimate human 3d poses", "Detect and track"], label="Methods", type="value", info="Select the model(s) you want")
-    check_file = gr.CheckboxGroup(choices = ["Estimate human 2d poses", "Estimate human 2d hand poses", "Estimate human 3d poses", "Detect and track"], label="Methods", type="value", info="Select the model(s) you want")
+    check_web =  gr.CheckboxGroup(choices = ["Detect and track", "Estimate human 2d poses", "Estimate human 2d hand poses", "Estimate human 3d poses"], label="Methods", type="value", info="Select the model(s) you want")
+    check_file = gr.CheckboxGroup(choices = ["Detect and track", "Estimate human 2d poses", "Estimate human 2d hand poses", "Estimate human 3d poses"], label="Methods", type="value", info="Select the model(s) you want")
 
     webcam = gr.Interface(
         fn=infer,
         inputs= [gr.Video(source="webcam", height=412), check_web],
-        outputs = [gr.PlayableVideo(), gr.PlayableVideo(), gr.PlayableVideo(), gr.PlayableVideo()],
+        outputs = [gr.Video(format='mp4'), gr.PlayableVideo(), gr.PlayableVideo(), gr.PlayableVideo()],
         title = 'Pose estimation', 
         description = 'Pose estimation on video',
         allow_flagging=False
@@ -129,7 +131,7 @@ def run():
     file = gr.Interface(
         infer,
         inputs = [gr.Video(source="upload", height=412), check_file],
-        outputs = [gr.PlayableVideo(), gr.PlayableVideo(), gr.PlayableVideo(), gr.PlayableVideo()],
+        outputs = [gr.Video(format='mp4'), gr.PlayableVideo(), gr.PlayableVideo(), gr.PlayableVideo()],
         allow_flagging=False
     )