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
zwq330205812
Shufflenet_v2_mmcv
Commits
6cf9c5ad
Commit
6cf9c5ad
authored
Dec 08, 2023
by
dcuai
Browse files
Update README.md
parent
06f785b1
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
19 additions
and
13 deletions
+19
-13
README.md
README.md
+19
-13
No files found.
README.md
View file @
6cf9c5ad
...
@@ -26,7 +26,7 @@ ShuffleNetV2 的网络结构可以分为两个部分:基础网络和分类器
...
@@ -26,7 +26,7 @@ ShuffleNetV2 的网络结构可以分为两个部分:基础网络和分类器
git
clone
--
recursive
http
:
//
developer
.
hpccube
.
com
/
codes
/
modelzoo
/
shufflenet_v2_mmcv
.
git
git
clone
--
recursive
http
:
//
developer
.
hpccube
.
com
/
codes
/
modelzoo
/
shufflenet_v2_mmcv
.
git
docker
pull
image
.
sourcefind
.
cn
:
5000
/
dcu
/
admin
/
base
/
pytorch
:
1.10
.
0
-
centos7
.
6
-
dtk
-
22.10
.
1
-
py37
-
latest
docker
pull
image
.
sourcefind
.
cn
:
5000
/
dcu
/
admin
/
base
/
pytorch
:
1.10
.
0
-
centos7
.
6
-
dtk
-
22.10
.
1
-
py37
-
latest
# <your IMAGE ID>用以上拉取的docker的镜像ID替换
# <your IMAGE ID>用以上拉取的docker的镜像ID替换
docker
run
--
shm
-
size
10
g
--
network
=
host
--
name
=
nit
-
pytorch
--
privileged
--
device
=/
dev
/
kfd
--
device
=/
dev
/
dri
--
group
-
add
video
--
cap
-
add
=
SYS_PTRACE
--
security
-
opt
seccomp
=
unconfined
-
v
$
PWD
/
shufflenet_v2_mmcv
:
/
home
/
shufflenet_v2_mmcv
-
it
<
your
IMAGE
ID
>
bash
docker
run
--
shm
-
size
10
g
--
network
=
host
--
name
=
shufflenet_v2
--
privileged
--
device
=/
dev
/
kfd
--
device
=/
dev
/
dri
--
group
-
add
video
--
cap
-
add
=
SYS_PTRACE
--
security
-
opt
seccomp
=
unconfined
-
v
$
PWD
/
shufflenet_v2_mmcv
:
/
home
/
shufflenet_v2_mmcv
-
it
<
your
IMAGE
ID
>
bash
cd
shufflenet_v2_mmcv
/
mmclassification
-
mmcv
cd
shufflenet_v2_mmcv
/
mmclassification
-
mmcv
pip
install
-
r
requirements
.
txt
pip
install
-
r
requirements
.
txt
...
@@ -37,7 +37,7 @@ pip install -r requirements.txt
...
@@ -37,7 +37,7 @@ pip install -r requirements.txt
```
plaintext
```
plaintext
cd shufflenet_v2_mmcv/docker
cd shufflenet_v2_mmcv/docker
docker build --no-cache -t densenet121_mmcv:latest .
docker build --no-cache -t densenet121_mmcv:latest .
docker run
--rm
--shm-size 10g --network=host --name=
megatron
--privileged --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v $PWD/../../shufflenet_v2_mmcv:/home/shufflenet_v2_mmcv -it
megatron
bash
docker run --shm-size 10g --network=host --name=
shufflenet_v2
--privileged --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v $PWD/../../shufflenet_v2_mmcv:/home/shufflenet_v2_mmcv -it
<your IMAGE ID>
bash
# 若遇到Dockerfile启动的方式安装环境需要长时间等待,可注释掉里面的pip安装,启动容器后再安装python库:pip install -r requirements.txt
# 若遇到Dockerfile启动的方式安装环境需要长时间等待,可注释掉里面的pip安装,启动容器后再安装python库:pip install -r requirements.txt
```
```
...
@@ -69,9 +69,15 @@ pip install -r requirements.txt
...
@@ -69,9 +69,15 @@ pip install -r requirements.txt
下载val数据:链接:https://pan.baidu.com/s/1oXsmsYahGVG3uOZ8e535LA?pwd=c3bc 提取码:c3bc 替换ImageNet数据集中的val目录,处理后的数据结构如下:
下载val数据:链接:https://pan.baidu.com/s/1oXsmsYahGVG3uOZ8e535LA?pwd=c3bc 提取码:c3bc 替换ImageNet数据集中的val目录,处理后的数据结构如下:
```
```
├── meta
data
├── train
├──imagenet
├── val
├── meta
├──val.txt
├──train.txt
...
├── train
├── val
```
```
## 训练
## 训练
...
@@ -82,7 +88,11 @@ pip install -r requirements.txt
...
@@ -82,7 +88,11 @@ pip install -r requirements.txt
./shufflenet_v2.sh
./shufflenet_v2.sh
## 精度
## result

### 精度
测试数据使用的是ImageNet数据集,使用的加速卡是DCU Z100L。
测试数据使用的是ImageNet数据集,使用的加速卡是DCU Z100L。
...
@@ -90,10 +100,6 @@ pip install -r requirements.txt
...
@@ -90,10 +100,6 @@ pip install -r requirements.txt
| :--: | :---------------------: |
| :--: | :---------------------: |
| 8 | top1:0.6960;top5:0.8895 |
| 8 | top1:0.6960;top5:0.8895 |
## result

## 应用场景
## 应用场景
### 算法类别
### 算法类别
...
@@ -104,10 +110,10 @@ pip install -r requirements.txt
...
@@ -104,10 +110,10 @@ pip install -r requirements.txt
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/shufflenet_v2_mmcv
https://developer.hpccube.com/codes/modelzoo/shufflenet_v2_mmcv
##
#
参考
## 参考
资料
https://github.com/open-mmlab/mmpretrain
https://github.com/open-mmlab/mmpretrain
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