Skip to content

Conversation

@kashif
Copy link

@kashif kashif commented May 22, 2020

Instead of parameters with grad=False, buffers is the way to go.

kashif added 4 commits May 22, 2020 09:42
Instead of parameters with grad=False, buffers is the way to go.
torch.Tensor will return float32 tensors
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

Successfully merging this pull request may close these issues.

1 participant