Skip to content
New issue

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

ROOT CAUSE?when used nn.Transpose3d , the shape of weight of transpose3d was consistency with nn.Transpose3D in torch. #939

Open
Yuxiang1990 opened this issue Jun 24, 2024 · 0 comments

Comments

@Yuxiang1990
Copy link

Hi,
refer to https://github.com/NVIDIA-AI-IOT/torch2trt/blob/master/torch2trt/converters/native_converters.py?plain=1#L439,
out_channels = int(weight.shape[0]) should be modified as out_channels = int(weight.shape[1]). ?

For transpose3d, weight was defined (in_channels,outchannels​, ...) which was exactly opposite of nn.conv3d.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant