Skip to content

Update readme.md with ViT training command #5086

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Dec 10, 2021
Merged

Update readme.md with ViT training command #5086

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 24 additions & 2 deletions references/classification/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,7 +125,7 @@ torchrun --nproc_per_node=8 train.py\
```
Here `$MODEL` is one of `regnet_x_400mf`, `regnet_x_800mf`, `regnet_x_1_6gf`, `regnet_y_400mf`, `regnet_y_800mf` and `regnet_y_1_6gf`. Please note we used learning rate 0.4 for `regent_y_400mf` to get the same Acc@1 as [the paper)(https://arxiv.org/abs/2003.13678).

### Medium models
#### Medium models
```
torchrun --nproc_per_node=8 train.py\
--model $MODEL --epochs 100 --batch-size 64 --wd 0.00005 --lr=0.4\
Expand All @@ -134,7 +134,7 @@ torchrun --nproc_per_node=8 train.py\
```
Here `$MODEL` is one of `regnet_x_3_2gf`, `regnet_x_8gf`, `regnet_x_16gf`, `regnet_y_3_2gf` and `regnet_y_8gf`.

### Large models
#### Large models
```
torchrun --nproc_per_node=8 train.py\
--model $MODEL --epochs 100 --batch-size 32 --wd 0.00005 --lr=0.2\
Expand All @@ -143,6 +143,28 @@ torchrun --nproc_per_node=8 train.py\
```
Here `$MODEL` is one of `regnet_x_32gf`, `regnet_y_16gf` and `regnet_y_32gf`.

### Vision Transformer

#### Base models
```
torchrun --nproc_per_node=8 train.py\
--model $MODEL --epochs 300 --batch-size 64 --opt adamw --lr 0.003 --wd 0.3\
--lr-scheduler cosineannealinglr --lr-warmup-method linear --lr-warmup-epochs 30\
--lr-warmup-decay 0.033 --amp --label-smoothing 0.11 --mixup-alpha 0.2 --auto-augment ra\
--clip-grad-norm 1 --ra-sampler --cutmix-alpha 1.0 --model-ema
```
Here `$MODEL` is one of `vit_b_16` and `vit_b_32`.

#### Large models
```
torchrun --nproc_per_node=8 train.py\
--model $MODEL --epochs 300 --batch-size 16 --opt adamw --lr 0.003 --wd 0.3\
--lr-scheduler cosineannealinglr --lr-warmup-method linear --lr-warmup-epochs 30\
--lr-warmup-decay 0.033 --amp --label-smoothing 0.11 --mixup-alpha 0.2 --auto-augment ra\
--clip-grad-norm 1 --ra-sampler --cutmix-alpha 1.0 --model-ema
```
Here `$MODEL` is one of `vit_l_16` and `vit_l_32`.

## Mixed precision training
Automatic Mixed Precision (AMP) training on GPU for Pytorch can be enabled with the [torch.cuda.amp](https://pytorch.org/docs/stable/amp.html?highlight=amp#module-torch.cuda.amp).

Expand Down