Data type (CMSIS-NN)

R2026b

(To be removed) Inference computation precision

Since R2022a

The coder.CMSISNNConfig object and its Data type (CMSIS-NN) parameter will be removed in a future release. Instead, create a deep learning configuration object by using the coder.DeepLearningConfig function with the target library set to "none", and set the CodeReplacementLibrary property of the code configuration object to "ARM Cortex-M". The CodeReplacementLibrary property requires Embedded Coder^®. The ARM^® Cortex^®-M code replacement library workflow, which uses the "none" target library, is more capable in MATLAB^® and Simulink^®, and supports a larger set of layers.

Description

App Configuration Pane: Deep Learning

Configuration Objects: coder.CMSISNNConfig

Precision of inference computations in supported layers.

Dependencies

To enable this parameter, you must set Deep learning library to CMSIS-NN.

Settings

int8: This setting is the default setting.

Programmatic Use

Property: DataType

Values: 'int8'

Default: 'int8'

Version History

Introduced in R2022a

collapse all

R2026b: To be removed

The coder.CMSISNNConfig object and its Data type (CMSIS-NN) parameter will be removed in a future release. Instead, create a deep learning configuration object by using the coder.DeepLearningConfig function with the target library set to "none", and set the CodeReplacementLibrary property of the code configuration object to "ARM Cortex-M". The CodeReplacementLibrary property requires Embedded Coder. The ARM Cortex-M code replacement library workflow, which uses the "none" target library, is more capable in MATLAB and Simulink, and supports a larger set of layers.