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
FastSAM_pytorch
Commits
87039a16
Commit
87039a16
authored
Aug 19, 2024
by
dcuai
Browse files
更换dtk24.04.1镜像
parent
cd33459a
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
7 additions
and
7 deletions
+7
-7
README.md
README.md
+7
-7
No files found.
README.md
View file @
87039a16
...
@@ -20,7 +20,7 @@
...
@@ -20,7 +20,7 @@
### Docker (方法一)
### Docker (方法一)
```
```
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:
1
.1
3.1
-centos7.6-dtk2
3.10
-py3
8
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:
2
.1
.0
-centos7.6-dtk2
4.04
-py3
10
# <your IMAGE ID>为以上拉取的docker的镜像ID替换
# <your IMAGE ID>为以上拉取的docker的镜像ID替换
docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt/hyhal --shm-size=32G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt/hyhal --shm-size=32G --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name docker_name imageID bash
cd /path/workspace/
cd /path/workspace/
...
@@ -42,10 +42,10 @@ docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt
...
@@ -42,10 +42,10 @@ docker run -it -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt
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.hpccube.com/tool/
```
```
DTK软件栈:dtk2
3.10
DTK软件栈:dtk2
4.04.1
python:python3.
8
python:python3.
10
pytorch:
1
.1
3.1
pytorch:
2
.1
.0
torchvision:0.1
4.1
torchvision:0.1
6.0
```
```
Tips:以上dtk软件栈、python、pytorch等DCU相关工具版本需要严格一一对应
Tips:以上dtk软件栈、python、pytorch等DCU相关工具版本需要严格一一对应
...
@@ -69,9 +69,9 @@ pip3 install git+https://github.com/openai/CLIP.git
...
@@ -69,9 +69,9 @@ pip3 install git+https://github.com/openai/CLIP.git
## 推理
## 推理
#### 单卡推理
#### 单卡推理
[
权重下载地址
](
https://pan.baidu.com/s/18KzBmOTENjByoWWR17zdiQ?pwd=0000
)
[
权重下载地址
](
https://pan.baidu.com/s/18KzBmOTENjByoWWR17zdiQ?pwd=0000
)
下载权重到当前文件夹,生成的图片默认存放在output文件夹下
```
```
HIP_VISIBLE_DEVICES=1 python Inference.py --model_path ./
weights/
FastSAM_X.pt --img_path ./images/dogs.jpg
HIP_VISIBLE_DEVICES=1 python Inference.py --model_path ./FastSAM_X.pt --img_path ./images/dogs.jpg
```
```
## result
## result
此处以Fast-SAM-x模型进行推理测试
<br>
此处以Fast-SAM-x模型进行推理测试
<br>
...
...
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