Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
ViT_pytorch
Commits
f197d0a5
Commit
f197d0a5
authored
Aug 26, 2024
by
chenych
Browse files
change scnet model in README
parent
44387c65
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
5 additions
and
4 deletions
+5
-4
README.md
README.md
+5
-4
No files found.
README.md
View file @
f197d0a5
...
@@ -64,24 +64,25 @@ pip install -r requirements.txt
...
@@ -64,24 +64,25 @@ pip install -r requirements.txt
```
```
## 训练
## 训练
下载预训练模型放在checkpoint目录下:
```
下载预训练模型
[
ViT-B_16.npz
](
http://113.200.138.88:18080/aimodels/findsource-dependency/ViT-B_16.git
)
放在checkpoint目录下。
wget https://storage.googleapis.com/vit_models/imagenet21k/ViT-B_16.npz
```
### 单机单卡
### 单机单卡
```
```
export HIP_VISIBLE_DEVICES=0
export HIP_VISIBLE_DEVICES=0
python3 -m torch.distributed.launch --nproc_per_node=1 --use-env train.py --name cifar10-100_500 --dataset cifar10 --model_type ViT-B_16 --pretrained_dir checkpoint/ViT-B_16.npz --train_batch_size 64 --num_steps 500
python3 -m torch.distributed.launch --nproc_per_node=1 --use-env train.py --name cifar10-100_500 --dataset cifar10 --model_type ViT-B_16 --pretrained_dir checkpoint/ViT-B_16.npz --train_batch_size 64 --num_steps 500
```
```
### 单机多卡
### 单机多卡
```
```
python3 -m torch.distributed.launch --nproc_per_node=8 --use-env train.py --name cifar10-100_500 --dataset cifar10 --model_type ViT-B_16 --pretrained_dir checkpoint/ViT-B_16.npz --train_batch_size 64 --num_steps 500
python3 -m torch.distributed.launch --nproc_per_node=8 --use-env train.py --name cifar10-100_500 --dataset cifar10 --model_type ViT-B_16 --pretrained_dir checkpoint/ViT-B_16.npz --train_batch_size 64 --num_steps 500
```
```
## result
## result


### 精度
### 精度
测试数据使用的是cifar10,使用的加速卡是DCU Z100L。
测试数据使用的是cifar10,使用的加速卡是DCU Z100L。
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment