Main Content

verifyCustomLayerModel

Class: dlhdl.ProcessorConfig
Namespace: dlhdl

Verify the functionality and accuracy of the custom layer by using the generated custom layer verification model

Since R2022a

Syntax

verifyCustomLayerModel(processorConfigObject)

Description

verifyCustomLayerModel(processorConfigObject) verifies the functionality of the custom layer and prediction accuracy of the network with the custom layer by using the custom layer verification model, which you generated by using the openCustomLayerModel method.

The openCustomLayerModel generates one default input network based on the custom layer settings in the deep learning processor configuration object and the generated network might not cover all the test scenarios. You can verify your custom layer implementation by opening the generated custom layer verification model and simulate different input networks or test the generated deep learning processor bitstream on hardware by deploying different input networks that use the custom layer. To simulate different input networks to the openCustomLayerModel method use the Network name-value argument. For example,

hW = dlhdl.ProcessorConfig;
openCustomLayerModel(Hw,Network=net);

Input Arguments

expand all

Processor configuration, specified as a dlhdl.ProcessorConfig object.

Examples

expand all

  1. Generate the verification model for your custom signum layer. For instructions, see Generate and Open Model for Custom Signum Layer. Leave the generated model file open.

  2. Verify the generated verification model for the custom signum layer by using the verifyCustomLayerModel method.

    verifyCustomLayerModel(hPC)
    ### Custom layer verification model simulation and validation begin.
    ### Compiling Simulink model 'dnnfpgaCustomLayerVerificationModel' ...
    ### Complete Simulink model 'dnnfpgaCustomLayerVerificationModel' compilation.
    Verification passed.
    ### Custom layer verification model simulation and validation complete.

Version History

Introduced in R2022a