Back to FabImage Deep Learning website

You are here: Start » Computer Vision » Deep Learning » WEAVER_DeployModel

WEAVER_DeployModel


Header: FILDL.h
Namespace: weaver
Module: DeepLearning

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

Syntax

C++
C#
 
void weaver::WEAVER_DeployModel
(
	const ftl::File& inModelFile,
	const ftl::Optional<fil::DeviceKind::Type>& inDeviceType,
	const int inDeviceIndex,
	const ftl::Array<fil::TensorDataOrdering::Type>& inDesiredOutputOrders,
	fil::WeaverModelId& outModelId
)

Parameters

Name Type Range Default Description
Input value inModelFile const File& A path to the model saved by Keras
Input value inDeviceType const Optional<DeviceKind::Type>& NIL A type of 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.. If not set, device depending on version (CPU/GPU) of installed Deep Learning add-on is selected.
Input value inDeviceIndex const int 0 - 0 An index of a device selected for deploying and executing the model.
Input value inDesiredOutputOrders const Array<TensorDataOrdering::Type>& A required data order of the output tensors
Output value outModelId WeaverModelId& Identifier of the deployed model

Errors

List of possible exceptions:

Error type Description
DomainError inModelFile cannot be empty in WEAVER_DeployModel.