aljaz/DALLE2-pytorch
1
1
Fork 0
mirror of https://github.com/lucidrains/DALLE2-pytorch.git synced 2025-12-21 18:44:20 +01:00
Code Issues Packages Projects Releases Wiki Activity

final update to dalle2 repository for a while - sampling from prior in chunks automatically with max_batch_size keyword given

Browse Source
This commit is contained in:
Phil Wang
2022-05-16 12:57:31 -07:00
parent c3d4a7ffe4
commit 13382885d9
3 changed files with 16 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@@ -820,8 +820,8 @@ clip = CLIP(
# mock data
text = torch.randint(0, 49408, (32, 256)).cuda()
images = torch.randn(32, 3, 256, 256).cuda()
text = torch.randint(0, 49408, (512, 256)).cuda()
images = torch.randn(512, 3, 256, 256).cuda()
# prior networks (with transformer)
@@ -854,7 +854,7 @@ diffusion_prior_trainer.update() # this will update the optimizer as well as th
# after much of the above three lines in a loop
# you can sample from the exponential moving average of the diffusion prior identically to how you do so for DiffusionPrior
image_embeds = diffusion_prior_trainer.sample(text) # (4, 512) - exponential moving averaged image embeddings
image_embeds = diffusion_prior_trainer.sample(text, max_batch_size = 4) # (512, 512) - exponential moving averaged image embeddings
```
## Bonus