Merge pull request #1007 from qwertyforce/patch-1

update arxiv link
pull/1014/head
Ross Wightman 3 years ago committed by GitHub
commit b20665d379
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -6,7 +6,7 @@ A PyTorch implement of the Hybrid Vision Transformers as described in:
- https://arxiv.org/abs/2010.11929 - https://arxiv.org/abs/2010.11929
`How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers` `How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers`
- https://arxiv.org/abs/2106.TODO - https://arxiv.org/abs/2106.10270
NOTE These hybrid model definitions depend on code in vision_transformer.py. NOTE These hybrid model definitions depend on code in vision_transformer.py.
They were moved here to keep file sizes sane. They were moved here to keep file sizes sane.
@ -360,4 +360,4 @@ def vit_base_resnet50d_224(pretrained=False, **kwargs):
model_kwargs = dict(embed_dim=768, depth=12, num_heads=12, **kwargs) model_kwargs = dict(embed_dim=768, depth=12, num_heads=12, **kwargs)
model = _create_vision_transformer_hybrid( model = _create_vision_transformer_hybrid(
'vit_base_resnet50d_224', backbone=backbone, pretrained=pretrained, **model_kwargs) 'vit_base_resnet50d_224', backbone=backbone, pretrained=pretrained, **model_kwargs)
return model return model

Loading…
Cancel
Save