fix

app.py

@@ -36,13 +36,13 @@ def fn(video: gr.Video):
       if i % detect_object_frame_steps == 0:
         print(f'Detect object: Frame {i}')
         detections = detect_object(detector, frame)
+        yield frame, None
       if len(frames) == classify_action_num_frames:
         print(f'Classify action: Until frame {i}')
         actions = classify_action(classifier, frames)
         frames = []
       frame = draw_boxes(frame, detections, actions)
       processed_frames.append(frame)
-      yield frame, None
     processed_clip = ImageSequenceClip(processed_frames, clip.fps)
     processed_clip.audio = clip.audio
     processed_clip.write_videofile(output, fps=clip.fps, audio_codec='aac', logger=None)