Intel® FPGA AI Suite: Getting Started Guide

ID 768970
Date 4/05/2023

A newer version of this document is available. Customers should click here to go to the newest version.

Document Table of Contents

6.3. Preparing a Model

A model must be converted from a framework (such as TensorFlow, Caffe, or Pytorch) into a pair of .bin and .xml files before the Intel® FPGA AI Suite compiler (dla_compiler command) can ingest the model.

The following commands download the ResNet-50 TensorFlow model and run Model Optimizer:
cd $COREDLA_WORK/demo/open_model_zoo
. venv/bin/activate
tools/downloader/ --name resnet-50-tf \
    --output_dir $COREDLA_WORK/demo/models/
tools/downloader/ --name resnet-50-tf \
    --download_dir $COREDLA_WORK/demo/models/ \
    --output_dir $COREDLA_WORK/demo/models/

These commands create .bin and .xml files in the demo/models/public/resnet-50-tf/FP32/ directory.

The directory $COREDLA_WORK/demo/open_model_zoo/models/public/resnet-50-tf/ contains two useful files that do not appear in the $COREDLA_ROOT/demo/models/ directory tree:
  • The file describes background information about the model.
  • The model.yml file shows the detailed command-line information given to Model Optimizer ( when it converts the model to a pair of .bin and .xml files

For a list OpenVINO™ Model Zoo models that the Intel® FPGA AI Suite supports, refer to the Intel® FPGA AI Suite IP Reference Manual .