Updated on 2025-05-29 GMT+08:00

Output Path

Description

The path for storing the batch prediction results. You can select an empty folder you created.

A manifest file will be generated in the output directory of the batch service.

  • Assume that the output path is //test-bucket/test/. The result is stored in the following path:
    OBS bucket or directory name
    ├── test-bucket
    │   ├── test
    │   │   ├── infer-result-{{task_id}}.manifest
    │   │   ├── infer-result-{{task_id}}
    │   │   │ ├── 1.jpg_result.txt
    │   │   │ ├── 2.jpg_result.txt
  • File format:
    • The file name is infer-result-{{task_id}}.manifest, where task_id is the batch task ID, which is the only ID for a batch service.
    • If a large number of files need to be processed, multiple manifest files may be generated with the same suffix .manifest and are distinguished by suffix, for example, infer-result-{{task_id}}_1.manifest.
    • The infer-result-{{task_id}} directory is created in the manifest directory to store the file processing result.
    • The manifest file content is in JSON format. Each line describes the output result of a piece of input data.
    • The content contains multiple fields:
      • source: input data description, which is the same as that of the input manifest file
      • result: file processing result, which can be SUCCESSFUL or FAILED
      • inference-loc: displayed when result is SUCCESSFUL. It is the output result path in the format of obs://{{Bucket name}}/{{Object name}}
      • error_message: displayed when result is FAILED. It is the output error information.