We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
At test_configs/I3D_RGB/i3d_kinetics400_3d_rgb_inception_v1_seg1_f64s1.py, I find out the mean and std is
img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
But in the source repo kinetics-i3d, whose ReadMe.md tells that:
From the RGB data, we added 1 and then divided by 2 to rescale between 0 and 1.
It seems the mean and std not match.
The mean and std of inception-v1 should be [128,128,128], [128,128,128], which may be mixed with the mean and std of Resnet-50.
The text was updated successfully, but these errors were encountered:
Thanks for pointing out the bug, I will provide a fix PR.
Sorry, something went wrong.
No branches or pull requests
At test_configs/I3D_RGB/i3d_kinetics400_3d_rgb_inception_v1_seg1_f64s1.py, I find out the mean and std is
img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
But in the source repo kinetics-i3d, whose ReadMe.md tells that:
It seems the mean and std not match.
The mean and std of inception-v1 should be [128,128,128], [128,128,128], which may be mixed with the mean and std of Resnet-50.
The text was updated successfully, but these errors were encountered: