Get pretrained model
Last updated
Was this helpful?
Last updated
Was this helpful?
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
.
/api/{projectId}/pretrained-model
Project ID
Impulse ID. If this is unset then the default impulse is used.
curl -L \
--url 'https://studio.edgeimpulse.com/v1/api/{projectId}/pretrained-model' \
--header 'x-api-key: YOUR_API_KEY'
{
"success": true,
"error": "text",
"specificDeviceSelected": true,
"availableModelTypes": [
"int8"
],
"model": {
"fileName": "text",
"profileJobId": 1,
"supportsTFLite": true,
"inputs": [
{
"name": "text",
"quantizationScale": 1,
"quantizationZeroPoint": 1,
"dataType": "int8",
"shape": [
1
]
}
],
"outputs": [
{
"name": "text",
"quantizationScale": 1,
"quantizationZeroPoint": 1,
"dataType": "int8",
"shape": [
1
]
}
],
"profileInfo": {
"float32": {
"device": "text",
"tfliteFileSizeBytes": 1,
"isSupportedOnMcu": true,
"timePerInferenceMs": 1,
"mcuSupportError": "text",
"memory": {
"tflite": {
"ram": 1,
"rom": 1,
"arenaSize": 1
},
"eon": {
"ram": 1,
"rom": 1,
"arenaSize": 1
},
"eonRamOptimized": {
"ram": 1,
"rom": 1,
"arenaSize": 1
}
}
},
"int8": {
"device": "text",
"tfliteFileSizeBytes": 1,
"isSupportedOnMcu": true,
"timePerInferenceMs": 1,
"mcuSupportError": "text",
"memory": {
"tflite": {
"ram": 1,
"rom": 1,
"arenaSize": 1
},
"eon": {
"ram": 1,
"rom": 1,
"arenaSize": 1
},
"eonRamOptimized": {
"ram": 1,
"rom": 1,
"arenaSize": 1
}
}
},
"table": {
"lowEndMcu": {
"description": "text",
"timePerInferenceMs": 1,
"supported": true,
"mcuSupportError": "text",
"memory": {
"tflite": {
"ram": 1,
"rom": 1
},
"eon": {
"ram": 1,
"rom": 1
},
"eonRamOptimized": {
"ram": 1,
"rom": 1
}
}
},
"highEndMcu": {
"description": "text",
"timePerInferenceMs": 1,
"supported": true,
"mcuSupportError": "text",
"memory": {
"tflite": {
"ram": 1,
"rom": 1
},
"eon": {
"ram": 1,
"rom": 1
},
"eonRamOptimized": {
"ram": 1,
"rom": 1
}
}
},
"highEndMcuPlusAccelerator": {
"description": "text",
"timePerInferenceMs": 1,
"supported": true,
"mcuSupportError": "text",
"memory": {
"tflite": {
"ram": 1,
"rom": 1
},
"eon": {
"ram": 1,
"rom": 1
},
"eonRamOptimized": {
"ram": 1,
"rom": 1
}
}
},
"mpu": {
"description": "text",
"timePerInferenceMs": 1,
"rom": 1,
"supported": true
},
"gpuOrMpuAccelerator": {
"description": "text",
"timePerInferenceMs": 1,
"rom": 1,
"supported": true
},
"variant": "int8"
}
}
},
"modelInfo": {
"input": {
"frequencyHz": 1,
"windowLengthMs": 1,
"inputType": "time-series"
},
"model": {
"modelType": "classification",
"labels": [
"text"
]
}
}
}
OK