This repository has been archived by the owner on Jun 22, 2022. It is now read-only.
No declaration of self.conv_stride #20
Comments
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Hi,
these 2 lines cannot work:
https://github.com/neptune-ml/steppy-toolkit/blob/master/toolkit/pytorch_transformers/architectures/unet.py#L251
https://github.com/neptune-ml/steppy-toolkit/blob/master/toolkit/pytorch_transformers/architectures/unet.py#L299
There is no place, where
self.conv_strideis declared. These UNets work only on assumption, that stride of convolutional layers is equal to 1, so I think that it should bestride = 1.Cheers
The text was updated successfully, but these errors were encountered: