GitHub - miaopas/ViT-pytorch: Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

miaopas / ViT-pytorch Public

forked from jeonsworld/ViT-pytorch

Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 51 Commits
img		img
models		models
utils		utils
.gitignore		.gitignore
b.png		b.png
fit error.ipynb		fit error.ipynb
layer5.png		layer5.png
requirements.txt		requirements.txt
test attention spectrum copy.ipynb		test attention spectrum copy.ipynb
test attention spectrum.ipynb		test attention spectrum.ipynb
test eigenvalue on permuted input.ipynb		test eigenvalue on permuted input.ipynb
test eigenvalue.ipynb		test eigenvalue.ipynb
train.py		train.py
train_lit.py		train_lit.py
train_lit_convoluted_input.py		train_lit_convoluted_input.py
train_lit_experiment.py		train_lit_experiment.py