Main Content

Quantization Workflow Prerequisites

This table lists the products required to quantize and deploy deep learning networks.

 Execution Environment
Development Host RequirementsFPGAGPU
Setup Toolkit Environment

hdlsetuptoolpath (HDL Coder)

The Calibrate workflow requires the MinGW C++ compiler or other compilers. For a list of supported compilers, see https://www.mathworks.com/support/requirements/supported-compilers.html

Note

The Calibrate workflow does not support the MinGW C compiler.

Setting Up the Prerequisite Products (GPU Coder)
Required Products
  • Deep Learning Toolbox™

  • Deep Learning HDL Toolbox™

Deep Learning Toolbox

Required Support Packages
  • Deep Learning Toolbox Model Quantization Library

  • Deep Learning HDL Toolbox Support Package for Xilinx® FPGA and SoC Devices

  • Deep Learning HDL Toolbox Support Package for Intel® FPGA and SoC Devices

Deep Learning Toolbox Model Quantization Library

Supported Networks and LayersSupported Networks, Layers and Boards (Deep Learning HDL Toolbox)Supported Networks and Layers (GPU Coder)
Deployment

Deep Learning HDL Toolbox

GPU Coder™

Additional Add Ons

MATLAB® Coder™ Interface for Deep Learning Libraries

  • GPU Coder Interface for Deep Learning Libraries

  • CUDA® enabled NVIDIA® GPU with compute capability 6.1, 6.3 or higher.

Workflow Specific Requirements

When the Deep Network Quantizer Hardware Settings is set to Simulate In MATLAB the Quantize and Validate workflow requires the Image Processing Toolbox™.