How to generate Verilog code from Deep Learning Network in MATLAB?

I have trained a Deep Learning Network in MATLAb, now I have to genearte a Verilog code for the same. I went through Deep Learning HDL Toolbox, there I found the methods to deploy the network on FPGA but did not get any method to generate a Verilog code. Please help.

[Giusy Giulia Tuccari]

Did you find any solution?

Answer 1

[Kiran Kintali]

Deep Learning Processor Customization and IP Generation

Configure, build, and generate custom bitstreams and processor IP cores, estimate and benchmark custom deep learning processor performance

Deep Learning HDL Toolbox™ provides functions to configure, build, and generate custom bitstreams and a custom processor IP. Obtain performance and resource utilization of a pretrained series network on the custom processor. Optimize the custom processor by using the estimation results.

https://www.mathworks.com/help/deep-learning-hdl/dlarchitecture.html

[Kiran Kintali]

Verilog option is available in the upcoming 21b pre-release as a dlhdl.ProcessorConfig processor config option.

[Saurabh Kumar Yadav]

Thank You for you response. But I am still unable to follow, how to generate verilog(.v) file

[Kiran Kintali]

https://www.mathworks.com/help/deep-learning-hdl/ug/custom-deep-learning-processor-generation-to-meet-performance-requirements.html

You need to follow these steps.

This example shows how to create a custom processor configuration and estimate the performance of a pretrained series network. You can then modify parameters of the custom processor configuration and re-estimate the performance. Once you have achieved your performance requirements you can generate a custom bitstream by using the custom processor configuration.

Currently VHDL is supported and Verilog generation support is available in a week or two with upcoming 21b pre-release.

[Saurabh Kumar Yadav]

VHDL will also do for me, but I did not find VHDL support either.

[Kiran Kintali]

please reach out to [e-mail] and someone from the MathWorks team can walk you through the steps and show you how to use the feature.