From c51293b1aa77d59471bb063ce54b29e3d914dfcb Mon Sep 17 00:00:00 2001 From: Kentaro Yoshioka Date: Mon, 11 Oct 2021 09:58:28 +0900 Subject: [PATCH] Update README.md --- README.md | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index a11bbf1..687f8bf 100644 --- a/README.md +++ b/README.md @@ -14,12 +14,14 @@ Added [ConvMixer]((https://openreview.net/forum?id=TVHS5Y4dNvM)) implementation. `python train_cifar10.py --patch 2` # vit-patchsize-2 -`python train_cifar10.py --net res18` # resnet18 - `python train_cifar10.py --net vit_timm --lr 1e-4` # train with pretrained vit `python train_cifar10.py --net convmixer --aug --n_epochs 200` # train with convmixer +`python train_cifar10.py --net res18` # resnet18 + +`python train_cifar10.py --net res18 --aug --n_epochs 200` # resnet18+randaug + # Results.. | | Accuracy | @@ -31,6 +33,7 @@ Added [ConvMixer]((https://openreview.net/forum?id=TVHS5Y4dNvM)) implementation. | ViT base (timm transfer) | 98.5% | | [ConvMixerTiny(no pretrain)](https://openreview.net/forum?id=TVHS5Y4dNvM) | 96.3% | | resnet18 | 93% | +| resnet18+randaug | 95% | # Used in.. * Vision Transformer Pruning [arxiv](https://arxiv.org/abs/2104.08500) [github](https://github.com/Cydia2018/ViT-cifar10-pruning)