ViT-Base (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-1k weights fine-tuned from in21k, source https://github.com/

ViT-Base model (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-21k weights @ 224x224, source https://github.com/googl

ViT-Base model (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-21k weights @ 224x224, source https://github.com/googl

ViT-Base (ViT-B/32) w/ SAM pretrained weights. Paper: https://arxiv.org/abs/2106.01548

ViT-Base (ViT-B/32) w/ SAM pretrained weights. Paper: https://arxiv.org/abs/2106.01548

ViT-Base model (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-1k weights fine-tuned from in21k @ 384x384, source htt

ViT-Base model (ViT-B/32) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-1k weights fine-tuned from in21k @ 384x384, source htt

ViT-Base (ViT-B/32+)

ViT-Base (ViT-B/32+)

ViT-Base (ViT-B/8) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-1k weights fine-tuned from in21k @ 224x224, source https://gi

ViT-Base (ViT-B/8) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-1k weights fine-tuned from in21k @ 224x224, source https://gi

ViT-Base (ViT-B/8) w/ DINO pretrained weights (no head) - https://arxiv.org/abs/2104.14294

ViT-Base (ViT-B/8) w/ DINO pretrained weights (no head) - https://arxiv.org/abs/2104.14294

ViT-Base model (ViT-B/8) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-21k weights @ 224x224, source https://github.com/google

ViT-Base model (ViT-B/8) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-21k weights @ 224x224, source https://github.com/google

ViT-Giant model (ViT-g/14) from `Scaling Vision Transformers` - https://arxiv.org/abs/2106.04560

ViT-Giant model (ViT-g/14) from `Scaling Vision Transformers` - https://arxiv.org/abs/2106.04560

ViT-Gigantic model (ViT-G/14) from `Scaling Vision Transformers` - https://arxiv.org/abs/2106.04560

ViT-Gigantic model (ViT-G/14) from `Scaling Vision Transformers` - https://arxiv.org/abs/2106.04560

ViT-Huge model (ViT-H/14) from original paper (https://arxiv.org/abs/2010.11929).

ViT-Huge model (ViT-H/14) from original paper (https://arxiv.org/abs/2010.11929).

ViT-Huge model (ViT-H/14) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-21k weights @ 224x224, source https://github.com/googl

ViT-Huge model (ViT-H/14) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-21k weights @ 224x224, source https://github.com/googl

ViT-Large model (ViT-L/14)

ViT-Large model (ViT-L/14)

ViT-Large model (ViT-L/16) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-1k weights fine-tuned from in21k @ 224x224, source ht

ViT-Large model (ViT-L/16) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-1k weights fine-tuned from in21k @ 224x224, source ht

ViT-Large model (ViT-L/16) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-21k weights @ 224x224, source https://github.com/goog

ViT-Large model (ViT-L/16) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-21k weights @ 224x224, source https://github.com/goog

ViT-Large model (ViT-L/16) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-1k weights fine-tuned from in21k @ 384x384, source ht

ViT-Large model (ViT-L/16) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-1k weights fine-tuned from in21k @ 384x384, source ht

ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929). No pretrained weights.

ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929). No pretrained weights.

ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-21k weights @ 224x224, source https://github.com/goog

ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-21k weights @ 224x224, source https://github.com/goog

ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-1k weights fine-tuned from in21k @ 384x384, source ht

ViT-Large model (ViT-L/32) from original paper (https://arxiv.org/abs/2010.11929). ImageNet-1k weights fine-tuned from in21k @ 384x384, source ht

ViT-Small w/ LayerScale + 18 x 2 (36 block parallel) config. Experimental, may remove. Based on `Three things everyone should know about Vision T

ViT-Small w/ LayerScale + 18 x 2 (36 block parallel) config. Experimental, may remove. Based on `Three things everyone should know about Vision T

ViT-Small (ViT-S/16) NOTE I've replaced my previous 'small' model definition and weights with the small variant from the DeiT paper

ViT-Small (ViT-S/16) NOTE I've replaced my previous 'small' model definition and weights with the small variant from the DeiT paper

ViT-Small (ViT-S/16) NOTE I've replaced my previous 'small' model definition and weights with the small variant from the DeiT paper

ViT-Small (ViT-S/16) NOTE I've replaced my previous 'small' model definition and weights with the small variant from the DeiT paper

ViT-Small (ViT-S/16) w/ DINO pretrained weights (no head) - https://arxiv.org/abs/2104.14294

ViT-Small (ViT-S/16) w/ DINO pretrained weights (no head) - https://arxiv.org/abs/2104.14294

ViT-Small (ViT-S/16) ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer. NOTE: this model has valid

ViT-Small (ViT-S/16) ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer. NOTE: this model has valid

ViT-Base w/ LayerScale + 36 x 1 (36 block serial) config. Experimental, may remove. Based on `Three things everyone should know about Vision Tran

ViT-Base w/ LayerScale + 36 x 1 (36 block serial) config. Experimental, may remove. Based on `Three things everyone should know about Vision Tran

ViT-Small (ViT-S/16) NOTE I've replaced my previous 'small' model definition and weights with the small variant from the DeiT paper

ViT-Small (ViT-S/16) NOTE I've replaced my previous 'small' model definition and weights with the small variant from the DeiT paper

ViT-Small (ViT-S/32)

ViT-Small (ViT-S/32)

ViT-Small (ViT-S/16) ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer. NOTE: this model has valid

ViT-Small (ViT-S/16) ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer. NOTE: this model has valid

ViT-Small (ViT-S/32) at 384x384.

ViT-Small (ViT-S/32) at 384x384.

ViT-Small (ViT-S/8) w/ DINO pretrained weights (no head) - https://arxiv.org/abs/2104.14294

ViT-Small (ViT-S/8) w/ DINO pretrained weights (no head) - https://arxiv.org/abs/2104.14294

ViT-Tiny (Vit-Ti/16)

ViT-Tiny (Vit-Ti/16)

ViT-Tiny (Vit-Ti/16)

ViT-Tiny (Vit-Ti/16)

ViT-Tiny (Vit-Ti/16). ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer. NOTE: this model has vali

ViT-Tiny (Vit-Ti/16). ImageNet-21k weights @ 224x224, source https://github.com/google-research/vision_transformer. NOTE: this model has vali

ViT-Tiny (Vit-Ti/16) @ 384x384.

ViT-Tiny (Vit-Ti/16) @ 384x384.