aljaz/DALLE2-pytorch
1
1
Fork 0
mirror of https://github.com/lucidrains/DALLE2-pytorch.git synced 2025-12-21 02:34:19 +01:00
Code Issues Packages Projects Releases Wiki Activity

update todo

Browse Source
This commit is contained in:
Phil Wang
2022-04-13 10:09:08 -07:00
committed by GitHub
parent 791d27326a
commit 9f1fe6c7ae
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@@ -38,8 +38,9 @@ Todo
## Todo ## Todo
- [ ] finish off gaussian diffusion class for latent embedding - allow for both prediction of epsilon as well as directly predicting embedding - [x] finish off gaussian diffusion class for latent embedding - allow for prediction of epsilon
- [ ] make sure it works end to end - [ ] add what was proposed in the paper, where DDPM objective for image latent embedding predicts x0 directly (reread vq-diffusion paper and get caught up on that line of work)
- [ ] make sure it works end to end to produce an output tensor, taking a single gradient step
- [ ] augment unet so that it can also be conditioned on text encodings (although in paper they hinted this didn't make much a difference) - [ ] augment unet so that it can also be conditioned on text encodings (although in paper they hinted this didn't make much a difference)
- [ ] look into Jonathan Ho's cascading DDPM for the decoder, as that seems to be what they are using. get caught up on DDPM literature - [ ] look into Jonathan Ho's cascading DDPM for the decoder, as that seems to be what they are using. get caught up on DDPM literature
- [ ] figure out all the current bag of tricks needed to make DDPMs great (starting with the blur trick mentioned in paper) - [ ] figure out all the current bag of tricks needed to make DDPMs great (starting with the blur trick mentioned in paper)