italosalgado14
commented
2 years ago Errata: I have used the following code to infer.
import torch import sys
print("RVM funcionara en: " + sys.argv[1])
model = torch.hub.load("PeterL1n/RobustVideoMatting", "mobilenetv3").cuda() # or "resnet50" convert_video = torch.hub.load("PeterL1n/RobustVideoMatting", "converter")
convert_video( model, # The loaded model, can be on any device (cpu or cuda). input_source=sys.argv[1], # A video file or an image sequence directory. downsample_ratio=None, # [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=12, # Process n frames at once for better parallelism. num_workers=1, # Only for image sequence input. Reader threads. progress=True # Print conversion progress.
)
PeterL1n
Thanks for the reply! Indeed my video is almost at 30 fps (29.4), which can cause the error you mention. But I have the same amount of frames both in the mask as in my original video (taking the videos to frames with python). I will preprocess the video to leave it at 30fps and I will comment here on how the solution was if it works for someone else.
Hello!. Thanks for the code. I have had some timing issues between the inferred output in the mask compared to the original video. I made this comparison by transforming my original video and the output video from masks to frames. I have obtained the same amount of frames in both processes, so the difference can be caused by a bad configuration of mine. My original video is 30fps and 1080x1920. If you have a suggestion I would appreciate it.