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
ResNet50_pytorch
Commits
03104ac6
"vscode:/vscode.git/clone" did not exist on "a9a5b14f3560596e34ce960e74ff29cc6b6a22e1"
Commit
03104ac6
authored
May 08, 2025
by
chenzk
Browse files
Update sf.md
parent
46dd29d9
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
6 additions
and
6 deletions
+6
-6
README.md
README.md
+6
-6
No files found.
README.md
View file @
03104ac6
...
...
@@ -10,13 +10,13 @@
ResNet50网络中包含了49个卷积层、1个全连接层等。


## 算法原理
ResNet50使用了多个具有残差连接的残差块来解决梯度消失或梯度爆炸问题,并使得网络可以向更深层发展。


## 环境配置
...
...
@@ -42,7 +42,7 @@ docker run --rm --shm-size 16g --network=host --name=resnet50_pytorch --privileg
### 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/
https://developer.
sourcefind.cn
/tool/
```
DTK驱动:dtk24.04.1
...
...
@@ -60,7 +60,7 @@ apex:1.1
下载ImageNet数据集:
[
imagenet-2012
](
https://image-net.org/download.php
)
参考
[
scrips/extract_ILSVRC.sh
](
https://developer.
hpccube.com
/codes/modelzoo/resnet50-pytorch/-/blob/main/scrips/extract_ILSVRC.sh
)
处理数据集,处理后数据集结构如下:
参考
[
scrips/extract_ILSVRC.sh
](
https://developer.
sourcefind.cn
/codes/modelzoo/resnet50-pytorch/-/blob/main/scrips/extract_ILSVRC.sh
)
处理数据集,处理后数据集结构如下:
```
data
...
...
@@ -115,7 +115,7 @@ mpirun --allow-run-as-root --bind-to none -np 4 single_process_amp.sh localhost
## result


## 精度
...
...
@@ -142,7 +142,7 @@ mpirun --allow-run-as-root --bind-to none -np 4 single_process_amp.sh localhost
# 源码仓库及问题反馈
https://developer.
hpccube.com
/codes/modelzoo/resnet50-pytorch
https://developer.
sourcefind.cn
/codes/modelzoo/resnet50-pytorch
# 参考资料
...
...
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