Update app.py

app.py

@@ -11,21 +11,20 @@ convert_video = torch.hub.load("PeterL1n/RobustVideoMatting", "converter")
 
 def inference(video):
   os.system('rm output.mp4')
-  clip = VideoFileClip(video).subclip(0, 5)
-  clip.write_videofile("output.mp4")
- # os.system('rm output.mp4')
- # os.system('ffmpeg -ss 00:00:00 -i '+ video +' -to 00:00:05 -c copy output.mp4')
+  #clip = VideoFileClip(video).subclip(0, 5)
+  #clip.write_videofile("output.mp4")
+  os.system('ffmpeg -ss 00:00:00 -i '+ video +' -to 00:00:05 -c copy output.mp4')
   convert_video(
       model,                           # The loaded model, can be on any device (cpu or cuda).
       input_source='output.mp4',        # A video file or an image sequence directory.
-      input_resize=(500, 500),       # [Optional] Resize the input (also the output).
+      input_resize=(250, 250),       # [Optional] Resize the input (also the output).
       downsample_ratio=0.25,           # [Optional] If None, make downsampled max size be 512px.
       output_type='video',             # Choose "video" or "png_sequence"
       output_composition='com.mp4',    # File path if video; directory path if png sequence.
       output_alpha="pha.mp4",          # [Optional] Output the raw alpha prediction.
       output_foreground="fgr.mp4",     # [Optional] Output the raw foreground prediction.
       output_video_mbps=4,             # Output video mbps. Not needed for png sequence.
-      seq_chunk=7,                    # Process n frames at once for better parallelism.
+      seq_chunk=12,                    # Process n frames at once for better parallelism.
       num_workers=1,                   # Only for image sequence input. Reader threads.
       progress=True                    # Print conversion progress.
   )