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

final thought

Browse Source
This commit is contained in:
Phil Wang
2022-05-21 10:47:45 -07:00
committed by GitHub
parent b432df2f7b
commit 8aab69b91e
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -1092,7 +1092,7 @@ This library would not have gotten to this working state without the help of
- [ ] for all model classes with hyperparameters that changes the network architecture, make it requirement that they must expose a config property, and write a simple function that asserts that it restores the object correctly
- [ ] for both diffusion prior and decoder, all exponential moving averaged models needs to be saved and restored as well (as well as the step number)
- [ ] read the paper, figure it out, and build it https://github.com/lucidrains/DALLE2-pytorch/issues/89
- [ ] use json schemas to manage config fields, start with decoder and move into diffusion prior
- [ ] use json schemas to manage config fields, start with decoder and move into diffusion prior - think about whether json schema can allow for both config-driven as well as CLI driven training (by constructing the click decorators from the schema)
## Citations