Question about Frame

Duration of video [s]: 1504.89 , recorded with 28.47 fps!
Overall # of frames: 42851 found with (before cropping) frame dimensions: 640 480
Starting to extract posture
26%|██████████████████████████████████████████████████ | 11128/42851 [05:20<15:51, 33.33it/s]Detected frames: 10710
26%|██████████████████████████████████████████████████ | 11128/42851 [05:21<15:15, 34.64it/s]
Saving results in C:\Users…\Desktop…
The videos are analyzed. Now your research can truly start!
You can create labeled videos with ‘create_labeled_video’.
If the tracking is not satisfactory for some videos, consider expanding the training set. You can use the function ‘extract_outlier_frames’ to extract any outlier frames!

I don’t know why the number of actual video frame and the detected frames is different here.

(OS Window 10 64 bit, Python 3.7.7, used GPU)

Thank you so much for your help by the way!

Hey @Ingyeo, pass robust_nframes=True in analyze_videos(). This is a bit slower but more robust as it does not read the number of frames from the metadata.