model package
Submodules
deploy
Transform a machine learning model into a library for an edge device.
Transforms a trained model into a library, package, or firmware ready to deploy on an embedded device. Can optionally apply post-training quantization if a representative data sample is uploaded.
Supported model formats:
Keras Model instance <https://www.tensorflow.org/api_docs/python/tf/keras/Model>_TensorFlow SavedModel <https://www.tensorflow.org/guide/saved_model>_ (as path to directory or.zipfile)ONNX model file <https://learn.microsoft.com/en-us/windows/ai/windows-ml/get-onnx-model>_ (as path to.onnxfile)TensorFlow Lite file <https://www.tensorflow.org/lite/guide>_ (as bytes, or path to any file that is not.zipor.onnx)
Representative data for quantization:
Must be a numpy array or
.npyfile.Each element must have the same shape as your model's input.
Must be representative of the range (maximum and minimum) of values in your training data.
Note: the available deployment options will change depending on the values given for model, model_output_type, and model_input_type. For example, the openmv deployment option is only available if model_input_type is set to ImageInput. If you attempt to deploy to an unavailable target, you will receive the error Could not deploy: deploy_target: ....
Parameters
model: pathlib.Path | str | bytes | Any
model_output_type: edgeimpulse.model.output_type.Classification | edgeimpulse.model.output_type.Regression | edgeimpulse.model.output_type.ObjectDetection
model_input_type: edgeimpulse.model.input_type.ImageInput | edgeimpulse.model.input_type.AudioInput | edgeimpulse.model.input_type.TimeSeriesInput | edgeimpulse.model.input_type.OtherInput | None = None
representative_data_for_quantization: pathlib.Path | str | bytes | Any | None = None
deploy_model_type: str | None = None
engine: str = 'tflite'
deploy_target: str = 'zip'
output_directory: str | None = None
api_key: str | None = None
timeout_sec: float | None = None
Return
_io.BytesIO
list_deployment_targets
List suitable deployment targets for the project associated with configured or provided api key.
Parameters
api_key: str | None = None
Return
List[str]
list_engines
List all the engines that can be passed to deploy()'s engine parameter.
Returns: List[str]: List of engines
Return
List[str]
list_model_types
List all the model types that can passed to deploy()'s deploy_model_type parameter.
Returns: List[str]: List of model types
Return
List[str]
list_profile_devices
List possible values for the device field when calling edgeimpulse.model.profile().
Parameters
api_key: str | None = None
Return
List[str]
profile
Profile the performance of a trained model on a range of embedded targets, or a specific device.
The response includes estimates of memory usage and latency for the model across a range of targets, including low-end MCU, high-end MCU, high-end MCU with accelerator, microprocessor unit (MPU), and a GPU or neural network accelerator. It will also include details of any conditions that preclude operation on a given type of device.
If you request a specific device, the results will also include estimates for that specific device. A list of devices can be obtained from edgeimpulse.model.list_profile_devices().
You can call .summary() on the response to obtain a more readable version of the most relevant information.
Parameters
model: pathlib.Path | str | bytes | Any
device: str | None = None
api_key: str | None = None
timeout_sec: float | None = None
Return
edgeimpulse.model._functions.profile.ProfileResponse
Last updated