10 Commits (28c0fa31fea5c503be63d79f74d8dca82c41da32)

Author	SHA1	Message	Date
Zhiyuan Chen	28c0fa31fe	Update vision_transformer.py	5 years ago
Zhiyuan Chen	ee3d8050c8	Align block with original design	5 years ago
Ross Wightman	b401952caf	Add newly added vision transformer large/base 224x224 weights ported from JAX official repo	5 years ago
Ross Wightman	61200db0ab	in_chans=1 working w/ pretrained weights for vision_transformer	5 years ago
Ross Wightman	f591e90b0d	Make sure num_features attr is present in vit models as with others	5 years ago
Ross Wightman	f944242cb0	Fix #262, num_classes arg mixup. Make vision_transformers a bit closer to other models wrt get/reset classfier/forward_features. Fix torchscript for ViT.	5 years ago
Ross Wightman	736f209e7d	Update vision transformers to be compatible with official code. Port official ViT weights from jax impl.	5 years ago
Ross Wightman	27a93e9de7	Improve test crop for ViT models. Small now 77.85, added base weights at 79.35 top-1.	5 years ago
Ross Wightman	d4db9e7977	Add small vision transformer weights. 77.42 top-1.	5 years ago
Ross Wightman	f31933cb37	Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.	5 years ago