readme.md 649 Bytes
Newer Older
yongshk's avatar
yongshk committed
1
2
# BEVformer

雍大凯's avatar
雍大凯 committed
3
4
5
## 快速执行

### 环境构建
yongshk's avatar
yongshk committed
6
7

```
雍大凯's avatar
雍大凯 committed
8
docker run -dit --network=host --name=bevformer --privileged --device=/dev/kfd --device=/dev/dri --ipc=host --shm-size=128G  --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -u root --ulimit stack=-1:-1 --ulimit memlock=-1:-1 -v /opt/hyhal:/opt/hyhal:ro -v /public/opendas/DL_DATA/zijia:/data:ro harbor.sourcefind.cn:5443/dcu/admin/base/custom:pytorch2.5.1-driver-bevformer
yongshk's avatar
yongshk committed
9
10
```

yongshk's avatar
yongshk committed
11
12
数据集已完成处理在乌镇集群/public/opendas/DL_DATA/zijia路径内

雍大凯's avatar
雍大凯 committed
13
### 代码执行
yongshk's avatar
yongshk committed
14
15
16
17
18
19

```
## 代码已经在容器/workspace下了
cd /workspace/BEVFormer
bash start_bevformer.sh
```