after successfully training a model, I wanted to improve it and use “extract_outlier_frames” to improve the results.
To do this, I analysed 4 of my 20 training/test videos. However, when I call extract_oulier_frames and enter “yes” for the first video, this happens: CalledProcessError: Command ‘ffprobe -i “C:\Users\ujtjf\Desktop\LAMA_Project\Testvideos\Ausfallschritt_1.avi” -show_entries format=duration -v quiet -of csv=“p=0”’ returned non-zero exit status 1.
I really don’t know what’s wrong, the rest works perfectly.
Many thanks for your ideas and tips.