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.

Sign up for GitHub

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

Jump to bottom

no need for hard coded self.batch_size #4

Open

Shumzi opened this issue Feb 1, 2021 · 0 comments · May be fixed by #5

Shumzi commented Feb 1, 2021

https://github.com/gentlemanman/fcrn_pytorch/blob/5cb562272d9939d9f9886b0fdb8768d84b998e90/fcrn.py#L51
you can just do:
batch_size = x.shape[0]
instead of hard coding it into the network.
if you hard code it, different batch sizes (e.g. in summary() or on the last batch of images) will screw up.

The text was updated successfully, but these errors were encountered:

Shumzi changed the title ~~no need for batch_size~~ no need for hard coded self.batch_size

Shumzi linked a pull request

that will close this issue

changed hardcoded batch size with per-batch #5

Open

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment