Commit ca6f1e2b authored by Rayyyyy's avatar Rayyyyy
Browse files

Add scnet datasets

parent 9df6c015
......@@ -25,10 +25,11 @@ docker run -it --network=host --name=unet --privileged --device=/dev/kfd --devic
cd /path/unet-pytorch
pip install -r requirements.txt
```
### Dockerfile(方法二)
```
docker build --no-cache -t unet:latest .
docker run -dit --network=host --name=unet --privileged --device=/dev/kfd --device=/dev/dri --ipc=host --shm-size=16G --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -u root --ulimit stack=-1:-1 --ulimit memlock=-1:-1 unet:latest
docker run -dit --network=host --name=unet --privileged --device=/dev/kfd --device=/dev/dri --ipc=host --shm-size=16G --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -u root --ulimit stack=-1:-1 --ulimit memlock=-1:-1 unet:latest
docker exec -it unet /bin/bash
cd /path/unet-pytorch
......@@ -53,10 +54,10 @@ pip install -r requirements.txt
## 数据集
`Carvana`
- https://www.kaggle.com/c/carvana-image-masking-challenge/data
- http://113.200.138.88:18080/aidatasets/project-dependency/carvana
下载命令:
```
```bash
bash scripts/download_data.sh
```
......@@ -86,11 +87,12 @@ python -m torch.distributed.launch --nproc_per_node 4 train_ddp.py
```
python predict.py -m model_path -i image.jpg -o output.jpg
```
## result
![rusult](https://developer.hpccube.com/codes/modelzoo/unet-pytorch/-/raw/main/doc/结果.png)
### 精度
测试数据:[test data](https://www.kaggle.com/c/carvana-image-masking-challenge/data),使用的加速卡:Z100L。(采用iou系数)
测试数据:[test data](http://113.200.138.88:18080/aidatasets/project-dependency/carvana),使用的加速卡:Z100L。(采用iou系数)
根据测试结果情况填写表格:
| Unet | 精度 |
......@@ -99,10 +101,10 @@ python predict.py -m model_path -i image.jpg -o output.jpg
## 应用场景
### 算法类别
`图像分割`
图像分割
### 热点应用行业
`医疗,交通,家居`
医疗,交通,家居
## 预训练权重
[SCNet AIModels - milesial-pytorch-unet-3.0](http://113.200.138.88:18080/aimodels/findsource-dependency/milesial-pytorch-unet-3.0)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment