Run MobileNet* SSD Int8 Inference Using TensorFlow* Model

Published: 11/09/2020  

Last Updated: 06/15/2022

Download Command



This document has instructions for running MobileNet V1 FP32 inference using Intel® Optimization for TensorFlow*.

The COCO validation dataset is used in these Mobilenet SSD quick start scripts. The inference and accuracy quick start scripts require the dataset to be converted into the TF records format. See the COCO dataset for instructions on downloading and preprocessing the COCO validation dataset.

Quick Start Scripts

Script name Description
int8_inference Runs inference on TF records and outputs performance metrics.
int8_accuracy Runs inference and checks accuracy on the results.

Bare Metal

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

For more information see the documentation on prerequisites in the TensorFlow models repo.

After installing the prerequisites, download and untar the model package. Set environment variables for the path to your DATASET_DIR and an OUTPUT_DIR where log files will be written, then run a quick start script.

DATASET_DIR=<path to the coco tf record file>
OUTPUT_DIR=<directory where log files will be written>

tar -xzf ssd-mobilenet-int8-inference.tar.gz
cd ssd-mobilenet-int8-inference

quickstart/<script name>.sh

Documentation and Sources

Get Started​
Main GitHub*
Release Notes
Get Started Guide

Code Sources
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

MobileNet SSD Int8 Inference TensorFlow* Container

View All Containers and Solutions 🡢

Product and Performance Information


Performance varies by use, configuration and other factors. Learn more at