You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When new VideoClips is created using VideoClips.subset() function, output_format of the original VideoClips is not taken into account.
Because of this, passing output_format="TCHW" argument to torchvision.datasets.hmdb51.HMDB51 does not work.
It seems that HMDB51 creates full_video_clips and video_clips for each fold of the dataset using subset() function.
Code snippet
Below is the code snippet for reproducing the bug:
馃悰 Describe the bug
When new
VideoClips
is created usingVideoClips.subset()
function,output_format
of the originalVideoClips
is not taken into account.Because of this, passing
output_format="TCHW"
argument totorchvision.datasets.hmdb51.HMDB51
does not work.It seems that
HMDB51
createsfull_video_clips
andvideo_clips
for eachfold
of the dataset usingsubset()
function.Code snippet
Below is the code snippet for reproducing the bug:
Output:
Possible solution:
Passing
output_format
of the originalVideoClips
when instantiating newVideoClips
inVideoClips.subset()
function.Versions
The text was updated successfully, but these errors were encountered: