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
baeceabc
Commit
baeceabc
authored
May 09, 2025
by
chenzk
Browse files
Update sf.md
parent
6bbca948
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
4 additions
and
4 deletions
+4
-4
README.md
README.md
+4
-4
No files found.
README.md
View file @
baeceabc
...
@@ -6,12 +6,12 @@
...
@@ -6,12 +6,12 @@
## 模型结构
## 模型结构
Vision Transformer先将图像用卷积进行分块以降低计算量,再对每一块进行展平处理变成序列,然后将序列添加位置编码和cls token,再输入多层Transformer结构提取特征,最后将cls tooken取出来通过一个MLP(多层感知机)用于分类。
Vision Transformer先将图像用卷积进行分块以降低计算量,再对每一块进行展平处理变成序列,然后将序列添加位置编码和cls token,再输入多层Transformer结构提取特征,最后将cls tooken取出来通过一个MLP(多层感知机)用于分类。


## 算法原理
## 算法原理
图像领域借鉴《Transformer is all you need!》算法论文中的Encoder结构提取特征,Transformer的核心思想是利用注意力模块attention提取特征:
图像领域借鉴《Transformer is all you need!》算法论文中的Encoder结构提取特征,Transformer的核心思想是利用注意力模块attention提取特征:


## 环境配置
## 环境配置
### Docker(方法一)
### Docker(方法一)
...
@@ -31,7 +31,7 @@ docker run --rm --shm-size 10g --network=host --name=megatron --privileged --dev
...
@@ -31,7 +31,7 @@ docker run --rm --shm-size 10g --network=host --name=megatron --privileged --dev
```
```
### Anaconda(方法三)
### Anaconda(方法三)
1、关于本项目DCU显卡所需的特殊深度学习库可从光合开发者社区下载安装: https://developer.
hpccube.com
/tool/
1、关于本项目DCU显卡所需的特殊深度学习库可从光合开发者社区下载安装: https://developer.
sourcefind.cn
/tool/
```
plaintext
```
plaintext
DTK驱动:dtk24.04.1
DTK驱动:dtk24.04.1
...
@@ -98,7 +98,7 @@ python3 -m torch.distributed.launch --nproc_per_node=8 train.py --name cifar10-1
...
@@ -98,7 +98,7 @@ python3 -m torch.distributed.launch --nproc_per_node=8 train.py --name cifar10-1
制造,能源,交通,网安
制造,能源,交通,网安
### 源码仓库及问题反馈
### 源码仓库及问题反馈
-
https://developer.
hpccube.com
/codes/modelzoo/vit_pytorch
-
https://developer.
sourcefind.cn
/codes/modelzoo/vit_pytorch
### 参考资料
### 参考资料
-
https://github.com/jeonsworld/ViT-pytorch
-
https://github.com/jeonsworld/ViT-pytorch
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