Get pretrained model

Get pretrained model

Receive info back about the earlier uploaded pretrained model (via uploadPretrainedModel) input/output tensors. If you want to deploy a pretrained model from the API, see startDeployPretrainedModelJob.

GEThttps://studio.edgeimpulse.com/v1/api/{projectId}/pretrained-model

Path parameters

projectId*integer

Project ID

Query parameters

Response

200

OK

Body

application/json

success*boolean

Whether the operation succeeded

errorstring

Optional error description (set if 'success' was false)

specificDeviceSelected*boolean

Whether a specific device was selected for performance profiling

availableModelTypes*array of KerasModelTypeEnum (enum)

The types of model that are available

modelobject

modelInfoobject

Request

JavaScriptCurlPython

const response = await fetch('https://studio.edgeimpulse.com/v1/api/{projectId}/pretrained-model', {
    method: 'GET',
    headers: {},
});
const data = await response.json();

Response

200

{
  "success": false,
  "error": "text",
  "specificDeviceSelected": false,
  "availableModelTypes": [
    "int8"
  ],
  "model": {
    "fileName": "text",
    "profileInfo": {
      "float32": {
        "device": "text",
        "tfliteFileSizeBytes": 0,
        "isSupportedOnMcu": false,
        "memory": {
          "tflite": {
            "ram": 0,
            "rom": 0,
            "arenaSize": 0
          },
          "eon": {
            "ram": 0,
            "rom": 0,
            "arenaSize": 0
          },
          "eonRamOptimized": {
            "ram": 0,
            "rom": 0,
            "arenaSize": 0
          }
        },
        "timePerInferenceMs": 0,
        "mcuSupportError": "text"
      },
      "int8": {
        "device": "text",
        "tfliteFileSizeBytes": 0,
        "isSupportedOnMcu": false,
        "memory": {
          "tflite": {
            "ram": 0,
            "rom": 0,
            "arenaSize": 0
          },
          "eon": {
            "ram": 0,
            "rom": 0,
            "arenaSize": 0
          },
          "eonRamOptimized": {
            "ram": 0,
            "rom": 0,
            "arenaSize": 0
          }
        },
        "timePerInferenceMs": 0,
        "mcuSupportError": "text"
      },
      "table": {
        "variant": "int8",
        "lowEndMcu": {
          "description": "text",
          "timePerInferenceMs": 0,
          "memory": {
            "tflite": {
              "ram": 0,
              "rom": 0
            },
            "eon": {
              "ram": 0,
              "rom": 0
            },
            "eonRamOptimized": {
              "ram": 0,
              "rom": 0
            }
          },
          "supported": false,
          "mcuSupportError": "text"
        },
        "highEndMcu": {
          "description": "text",
          "timePerInferenceMs": 0,
          "memory": {
            "tflite": {
              "ram": 0,
              "rom": 0
            },
            "eon": {
              "ram": 0,
              "rom": 0
            },
            "eonRamOptimized": {
              "ram": 0,
              "rom": 0
            }
          },
          "supported": false,
          "mcuSupportError": "text"
        },
        "highEndMcuPlusAccelerator": {
          "description": "text",
          "timePerInferenceMs": 0,
          "memory": {
            "tflite": {
              "ram": 0,
              "rom": 0
            },
            "eon": {
              "ram": 0,
              "rom": 0
            },
            "eonRamOptimized": {
              "ram": 0,
              "rom": 0
            }
          },
          "supported": false,
          "mcuSupportError": "text"
        },
        "mpu": {
          "description": "text",
          "timePerInferenceMs": 0,
          "rom": 0,
          "supported": false
        },
        "gpuOrMpuAccelerator": {
          "description": "text",
          "timePerInferenceMs": 0,
          "rom": 0,
          "supported": false
        }
      }
    },
    "inputs": [
      {
        "dataType": "int8",
        "name": "text",
        "shape": [
          0
        ],
        "quantizationScale": 0,
        "quantizationZeroPoint": 0
      }
    ],
    "outputs": [
      {
        "dataType": "int8",
        "name": "text",
        "shape": [
          0
        ],
        "quantizationScale": 0,
        "quantizationZeroPoint": 0
      }
    ],
    "profileJobId": 0,
    "supportsTFLite": false
  },
  "modelInfo": {
    "input": {
      "inputType": "time-series",
      "frequencyHz": 0,
      "windowLengthMs": 0
    },
    "model": {
      "modelType": "classification",
      "labels": [
        "text"
      ]
    }
  }
}