aljaz/DALLE2-pytorch
1
1
Fork 0
mirror of https://github.com/lucidrains/DALLE2-pytorch.git synced 2025-12-24 03:54:19 +01:00
Code Issues Packages Projects Releases Wiki Activity

todo

Browse Source
This commit is contained in:
Phil Wang
2022-04-18 12:18:19 -07:00
committed by GitHub
parent 00ae50999b
commit 7214df472d
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@@ -414,6 +414,7 @@ Offer training wrappers
- [ ] make unet more configurable
- [ ] figure out some factory methods to make cascading unet instantiations less error-prone
- [ ] offload unets not being trained on to CPU for memory efficiency (for training each resolution unets separately)
- [ ] become an expert with unets, port learnings over to https://github.com/lucidrains/x-unet
- [ ] train on a toy task, offer in colab
- [ ] add attention to unet - apply some personal tricks with efficient attention - use the sparse attention mechanism from https://github.com/lucidrains/vit-pytorch#maxvit
- [ ] build out latent diffusion architecture in separate file, as it is not faithful to dalle-2 (but offer it as as setting)