Calibration result file path (CMSIS-NN)
R2026b(To be removed) Location of calibration MAT file
Since R2022a
The coder.CMSISNNConfig object and its Calibration result file
path (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
Location of the MAT file containing the calibration data.
When performing quantization, the calibrate (Deep Learning Toolbox)
function exercises the network and collects the dynamic ranges of the weights and biases
in the convolution and fully connected layers of the network and the dynamic ranges of
the activations in all layers of the network. To generate code for the optimized
network, save the results from the calibrate function to a MAT file
and specify the location of this MAT file to the code generator using this
property.
Dependencies
To enable this parameter, you must set Deep learning
library to CMSIS-NN.
Settings
- character vector, string scalar
Path to the folder that contains the calibration data.
Programmatic Use
Property:
CalibrationResultFile |
Values: '' | character
vector | string scalar |
Default: '' |
Version History
Introduced in R2022aSee Also
calibrate (Deep Learning Toolbox) | coder.CMSISNNConfig
