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

add efficient_unet and update others #11

Open

odb9402 wants to merge 2 commits into main from add_efficient_unet

odb9402 commented Oct 25, 2023

Add EfficientUNet2DConditionModel and related blocks
- Memory (for forward-backward) efficient UNet for super-resolution tasks, originally proposed by Google (Imagen)
Remove type keyword for Linear(*, dtype=) since it raises error for the old version of torch (Linear module does not have dtype kwarg
Add encoder_attention_mask to the UNet2DConditionModel and related blocks

(MAF specific) bypassing the error in torch.clamp---currently, torch.clamp only allows tensor datatype, not float---with minimum and maximum

odb9402 added 2 commits

October 25, 2023 14:09


          add efficient_unet and update others

4add4d4


          remove einsum

ac58d59

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

Labels

None yet