Base class

class neurio.devices.device.Device(port: any, name: str = '', log_dir: str | None = None, **kwargs)

Superclass for all devices.

prepare_for_inference(model, **kwargs)

Prepare the device for inference. This function should be called before any inference.

Parameters:

• model – model to deploy on the device

• kwargs – other parameters relevant for the preparation of the device

infer(input_x, batch_size: int, **kwargs)

Run inference on the device and measures associated performance metrics.

Parameters:

• input_x – input data to infer

• batch_size – batch size

• kwargs – other parameters

Returns:

tuple: (inference_results: np.array, profiler: Profiler)

Raises:

DeviceNotReadyException – if the device is not ready for inference.

predict(input_x, batch_size, **kwargs)

Run inference on the device and measures associated performance metrics.

Parameters:

• input_x – input data to infer

• batch_size – batch size

• kwargs – other parameters

Returns:

the inference results

abstract is_alive(timeout: int = 20) → bool

Check if the device is alive

Parameters:

timeout – timeout in seconds

Returns:

Return true if the device is alive (connected), false otherwise