V7v7labs

Create ModelTemplate

post/model_templates

Request

  • Base URL
    https://darwin.v7labs.com/ai
  • URL
    https://darwin.v7labs.com/ai/model_templates
  • Auth
    API key in header Authorization

Request body

namestring

The name of the ModelTemplate

typestring

The ModelTemplate type. Wind currently supports "instance_segmentation", "object_detection", "classification" and "auto_annotation"

docker_imagestring

The Docker image URI of the ModelTemplate Integration

devicesstring json

A list of supported devices for the ModelTemplate, among "cpu" and "gpu"

load_paramsstring json

List of optional parameters needed by the Model Template Integration to successfully load the model before inference

infer_paramsstring json

List of optional parameters needed by the Model Template Integration to successfully run inference

train_paramsstring json

List of optional parameters needed by the Model Template Integration to successfully start a TrainingSession

Response

200

namestring
typestring
docker_imagestring
devicesstring[]

Example response

{
  "name": "My Model Template",
  "type": "instance_segmentation",
  "docker_image": "1234567890.dkr.ecr.eu-west-1.amazonaws.com/models/my-model:latest",
  "devices": [
    "cpu"
  ],
  "train_params": {
    "config_file": "/path/to/config.yaml"
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.