mirror/cube-studio
2
0
Fork 0
mirror of https://github.com/tencentmusic/cube-studio.git synced 2024-12-15 06:09:57 +08:00
Code Issues Packages Projects Releases Wiki Activity
93388ec37f
cube-studio/job-template/job/horovod
History
pengluan d2724dde33 补全配置文件描述
2022-06-17 16:58:10 +08:00
..
build.sh 添加horovod分布式 2022-06-14 13:20:50 +08:00
Dockerfile 添加horovod分布式 2022-06-14 13:20:50 +08:00
README.md 补全配置文件描述 2022-06-17 16:58:10 +08:00
start.py 添加horovod分布式 2022-06-14 13:20:50 +08:00
tensorflow-mnist.yaml 添加horovod分布式 2022-06-14 13:20:50 +08:00

README.md

horovod 模板

镜像：ccr.ccs.tencentyun.com/cube-studio/horovod:20210401 k8s账号: kubeflow-pipeline 启动参数：

{
    "参数": {
        "--num_worker": {
            "type": "str",
            "item_type": "str",
            "label": "分布式worker的数目",
            "require": 1,
            "choice": [],
            "range": "",
            "default": 2,
            "placeholder": "",
            "describe": "分布式worker的数目",
            "editable": 1,
            "condition": "",
            "sub_args": {}
        },
        "--command": {
            "type": "str",
            "item_type": "str",
            "label": "训练启动命令",
            "require": 1,
            "choice": [],
            "range": "",
            "default": "python /horovod/examples/tensorflow2/tensorflow2_mnist.py",
            "placeholder": "",
            "describe": "训练启动命令",
            "editable": 1,
            "condition": "",
            "sub_args": {}
        },
        "--work_images": {
            "type": "str",
            "item_type": "str",
            "label": "worker的运行镜像",
            "require": 1,
            "choice": [],
            "range": "",
            "default": "ccr.ccs.tencentyun.com/cube-studio/horovod:20210401",
            "placeholder": "",
            "describe": "worker的运行镜像",
            "editable": 1,
            "condition": "",
            "sub_args": {}
        }
    }
}