WEAVER_DeployModel


Header: FILDL.h
Namespace: weaver
Module: DeepLearning

Loads a deep learning model and prepares its execution on a specific target device.

Syntax

void weaver::WEAVER_DeployModel
(
	const ftl::File& inModelFile,
	const ftl::Optional<fil::DeviceType::Type>& inTargetDevice,
	const ftl::Array<ftl::Optional<fil::TensorDataOrdering::Type>>& inDesiredOutputOrders,
	fil::WeaverModelId& outModelId
)

Parameters

Name Type Default Description
Input value
inModelFile const File& A path to the model saved by Keras
Input value
inTargetDevice const Optional<DeviceType::Type>& NIL A device selected for deploying and executing the model. If not set, device depending on version (CPU/GPU) of installed Deep Learning Add-on is selected.
Input value
inDesiredOutputOrders const Array<Optional<TensorDataOrdering::Type>>& A required data order of the output tensors
Output value
outModelId WeaverModelId& Identifier of the deployed model