3 results found Sort:

xxxnell
how-do-vits-work xxxnell
79
808
apache-2.0
7
(ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"
pytorch transformer loss-landscape self-attention vision-transformer
Created 2021-03-09
129 commits to transformer branch, last one 2 years ago
logancyang
loss-landscape-anim logancyang
23
141
mit
3
Create animations for the optimization trajectory of neural nets
pca pytorch neural-nets loss-landscape pytorch-lightning optimization-trajectory
Created 2021-01-04
64 commits to master branch, last one 11 months ago
sayakpaul
Sharpness-Aware-Minimization-TensorFlow sayakpaul
12
60
unknown
3
Implements sharpness-aware minimization (https://arxiv.org/abs/2010.01412) in TensorFlow 2.
tensorflow generalization loss-landscape computer-vision tpu-acceleration deep-neural-networks
Created 2021-02-25
22 commits to main branch, last one 3 years ago