Run the Faster R-CNN Int8 Inference with a TensorFlow* Model Package

Download Command

wget https://storage.googleapis.com/intel-optimized-tensorflow/models/v2_3_0/faster-rcnn-int8-inference.tar.gz

Description

The COCO validation dataset is used in the Faster R-CNN quick start scripts. The scripts require that the dataset has been converted to the TensorFlow* records format. See the COCO dataset for instructions on downloading and preprocessing the COCO validation dataset.

Set the DATASET_DIR to point to this directory when running Faster R-CNN .

Quick Start Scripts

Bare Metal

To run on bare metal, the following prerequisites must be installed in your environment:

• Python* 3
• Git
• Numactl
• GNU Wget
• Protobuf Compilation
• Intel® Optimization for TensorFlow* 1.15.2
• Cython
• Contextlib2
• Jupyter*
• Lxml
• Matplotlib
• Pillow 7.1.0
• Pycocotools

Clone the TensorFlow* Model Garden repository using the specified tag, and save the path to the TF_MODELS_DIR environment variable.

# Clone the TF models repo
git clone https://github.com/tensorflow/models.git
pushd models
git checkout tags/v1.12.0
export TF_MODELS_DIR=$(pwd)
popd

After installing the prerequisites, download and extract the model package, which includes the pretrained model and scripts needed to run inference. Set environment variables for the path to your DATASET_DIR (where the coco TensorFlow* records file is located) and an OUTPUT_DIR where log files will be written, then run a quick start script.

wget https://storage.googleapis.com/intel-optimized-tensorflow/models/v2_3_0/faster-rcnn-int8-inference.tar.gz
tar -xzf faster_rcnn-int8-inference.tar.gz
cd faster_rcnn-int8-inference

export DATASET_DIR=<path to the coco dataset>
export OUTPUT_DIR=<directory where log files will be written>

quickstart/<script name>.sh

Documentation and Sources

Get Started
Docker* Repository
Main GitHub*
Readme
Release Notes
Get Started Guide

Code Sources
Dockerfile
Report Issue

License Agreement

LEGAL NOTICE: By accessing, downloading or using this software and any required dependent software (the “Software Package”), you agree to the terms and conditions of the software license agreements for the Software Package, which may also include notices, disclaimers, or license terms for third party software included with the Software Package. Please refer to the license file for additional details.

Related Containers and Solutions

Faster RCNN Int8 Inference TensorFlow* Container

View All Containers and Solutions 🡢