Calibration result file path (ARM Compute)

R2026b

(To be removed) Location of calibration MAT file

The coder.ARMNEONConfig object and its Calibration result file path (ARM Compute) 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" to generate generic C/C++ code that does not depend on any third-party library. The "none" target library workflow is more capable in MATLAB® and Simulink®, and supports a larger set of layers.

Description

App Configuration Pane: Deep Learning

Configuration Objects: coder.ARMNEONConfig

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 both these parameters:

  • Deep learning library to ARM Compute

  • Data type to int8

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 R2021a

collapse all

See Also

(Deep Learning Toolbox) |