aljaz/DALLE2-pytorch
1
1
Fork 0
mirror of https://github.com/lucidrains/DALLE2-pytorch.git synced 2025-12-19 17:54:20 +01:00
Code Issues Packages Projects Releases Wiki Activity

take care of gradient accumulation automatically for researchers, by passing in a max_batch_size on the decoder or diffusion prior trainer forward

Browse Source
This commit is contained in:
Phil Wang
2022-05-14 17:04:09 -07:00
parent b494ed81d4
commit b0cd5f24b6
3 changed files with 85 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
setup.py
View File

@@ -10,7 +10,7 @@ setup(
'dream = dalle2_pytorch.cli:dream'
],
},
version = '0.2.24',
version = '0.2.26',
license='MIT',
description = 'DALL-E 2',
author = 'Phil Wang',