Previous page Next page

On the page:


General info

Method

POST /IP address:port/<api_ver>/inference/image

DescriptionThe query is used to perform inference (classification check) on an image using a trained neural model. The query accepts an image (in the format: .jpeg, .jpg, .png, or .webp)

Sample request

POST http://localhost:5000/v1.3/inference/image
{
  "task_id": "6407bfd7144f37e141b786e2acf4faf2822cc48f296f5047e58c9e536874f4ec",
  "image_url": "https://example.com/images/lion.jpg"
}

where:

ParameterDescription
task_id

A unique identifier of the task (uid), which can be obtained using a task list query (see Get the list of tasks)

image_url

Link to an image

Sample response

{
    "message": "Done",
    "probabilities": {
         "AFRICAN_LEOPARD": 0,
         "CARACAL": 0,
         "LIONS": 100
     }
}

Response in case of error:

{ "error": "error description" }


  • No labels