创建批量预测任务

1. 接口描述

接口请求域名： tione.tencentcloudapi.com 。

创建批量预测任务

默认接口请求频率限制：20次/秒。

2. 输入参数

以下请求参数列表仅列出了接口请求参数和部分公共参数，完整公共参数列表见 公共请求参数。

3. 输出参数

4. 示例

示例1 CreateBatchTask

批量预测示例请求

输入示例

POST / HTTP/1.1
Host: tione.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: CreateBatchTask
<公共请求参数>

{
    "BatchTaskName": "task-xx",
    "ChargeType": "POSTPAID_BY_HOUR",
    "ResourceGroupId": "trsg-c7xxxx",
    "ResourceConfigInfo": {
        "Role": "WORKER",
        "Cpu": 1,
        "Memory": 1,
        "GpuType": "A",
        "Gpu": 1,
        "InstanceType": "TI.S.LARGE.POST-XXX",
        "InstanceNum": 1
    },
    "Tags": [
        {
            "TagKey": "abc",
            "TagValue": "def"
        }
    ],
    "ModelInfo": {
        "ModelId": "abc-id",
        "ModelName": "Pytorch",
        "ModelVersionId": "mv-v2-abcdef",
        "ModelVersion": "v2",
        "ModelSource": "cos",
        "CosPathInfo": {
            "Bucket": "test-sh-123",
            "Region": "ap-shanghai",
            "Paths": [
                "test/model"
            ]
        },
        "AlgorithmFramework": "torch",
        "ModelType": "ACCELERATE"
    },
    "ImageInfo": {
        "ImageType": "CCR",
        "ImageUrl": "ccr.tencentyun.com/a/b/c",
        "RegistryRegion": "",
        "RegistryId": ""
    },
    "CodePackage": {
        "Bucket": "testbkt-1234",
        "Region": "ap-shanghai",
        "Paths": [
            "test/model/code_Path"
        ]
    },
    "StartCmd": "python3 /opt/ml/code/model_service.py",
    "StartCmdBase64": "L2FwcC9ydW4uc2g=",
    "DataConfigs": [
        {
            "MappingPath": "",
            "DataSourceType": "",
            "DataSetSource": {
                "Id": "12345678"
            },
            "COSSource": {
                "Bucket": "test-bkt-1234",
                "Region": "ap-shanghai",
                "Paths": [
                    "test/data/"
                ]
            },
            "CFSSource": {
                "Id": "12345",
                "Path": "/data"
            },
            "HDFSSource": {
                "Id": "12345",
                "Path": "test/hdfs_path/"
            }
        }
    ],
    "Outputs": [
        {
            "MappingPath": "",
            "DataSourceType": "cos",
            "DataSetSource": {
                "Id": "ds-12345-xx"
            },
            "COSSource": {
                "Bucket": "testbkt-12345",
                "Region": "ap-shanghai",
                "Paths": [
                    "tests/outputs/"
                ]
            },
            "CFSSource": {
                "Id": "",
                "Path": ""
            },
            "HDFSSource": {
                "Id": "",
                "Path": ""
            }
        }
    ],
    "LogEnable": true,
    "LogConfig": {
        "LogsetId": "123456",
        "TopicId": "topic-12345"
    },
    "VpcId": "12345",
    "SubnetId": "12345",
    "Remark": "",
    "CallbackUrl": ""
}

输出示例

{
    "Response": {
        "BatchTaskId": "task-123-xx",
        "RequestId": "abcdef-1234"
    }
}

5. 开发者资源

腾讯云 API 平台

腾讯云 API 平台 是综合 API 文档、错误码、API Explorer 及 SDK 等资源的统一查询平台，方便您从同一入口查询及使用腾讯云提供的所有 API 服务。

API Inspector

用户可通过 API Inspector 查看控制台每一步操作关联的 API 调用情况，并自动生成各语言版本的 API 代码，也可前往 API Explorer 进行在线调试。

SDK

云 API 3.0 提供了配套的开发工具集（SDK），支持多种编程语言，能更方便的调用 API。

• Tencent Cloud SDK 3.0 for Python: GitHub Gitee
• Tencent Cloud SDK 3.0 for Java: GitHub Gitee
• Tencent Cloud SDK 3.0 for PHP: GitHub Gitee
• Tencent Cloud SDK 3.0 for Go: GitHub Gitee
• Tencent Cloud SDK 3.0 for Node.js: GitHub Gitee
• Tencent Cloud SDK 3.0 for .NET: GitHub Gitee
• Tencent Cloud SDK 3.0 for C++: GitHub Gitee
• Tencent Cloud SDK 3.0 for Ruby: GitHub Gitee

命令行工具

• Tencent Cloud CLI 3.0

6. 错误码

以下仅列出了接口业务逻辑相关的错误码，其他错误码详见 公共错误码。