Calibration result file path (ARM Compute)
Location of calibration MAT file
Since R2021a
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
See Also
calibrate
(Deep Learning Toolbox) | coder.ARMNEONConfig