RpcCommandsclassRPC commandsEvbBackendclassRPC commands
RpcCommands()RPC commands
These commands are used to send data to the EVB.
SEND_MODEL: int = 0Send model to EVB
SEND_INPUT: int = 1Send input data to EVB
FETCH_OUTPUT: int = 2Fetch output data from EVB
FETCH_STATUS: int = 3Fetch status from EVB
PERFORM_INFERENCE: int = 4Perform inference on
EvbBackend(params: TaskParams) -> NoneEVB inference engine backend
This backend leverages Ambiq SoCs to run inference on the edge. The model, inputs, and outputs are sent to the EVB using eRPC.
By default, the backend will scan serial ports looking for the EVB. Therefore, the EVB must be connected and running prior to using this backend.
Parameters
| Name | Type | Default | Description |
|---|---|---|---|
params | HKTaskParams | Required | Task parameters |
Open connection to EVB
open()Open connection to EVB
The following steps are performed:
Close connection to EVB
close()Close connection to EVB
This method will close the connection to the EVB.
Send model to EVB
send_model()Send model to EVB
This method sends the model to the EVB using eRPC. The TFLite flatbuffer will be read from disk and sent to the EVB.
Set inputs for inference
set_inputs(inputs: npt.NDArray)Set inputs for inference
The inputs are flattened and sent to the EVB using eRPC.
Parameters
| Name | Type | Default | Description |
|---|---|---|---|
inputs | npt.NDArray | Required | Inputs for inference |
Perform inference
perform_inference()Perform inference
This method sends the inference command to the EVB and waits for the inference to complete.
Get outputs from inference
get_outputs() -> npt.NDArrayGet outputs from inference
The outputs are fetched from the EVB and converted to a numpy array.
Returns
| Type | Description |
|---|---|
npt.NDArray | npt.NDArray: Outputs from inference |