Optimize a MobileNet* V1 FP32 Inference Container with TensorFlow*

Published: 10/22/2020  

Last Updated: 06/15/2022

Pull Command

docker pull intel/image-recognition:tf-latest-mobilenet-v1-fp32-inference

Description

This document has instructions for running MobileNet* v1 FP32 inference using Intel® Optimization for TensorFlow*.

Note that the ImageNet dataset is used in these MobileNet* v1 examples.  Download and preprocess the ImageNet dataset using the instructions here. After running the conversion script you should have a directory with the ImageNet dataset in the TensorFlow* records format.

Quick Start Scripts

Script name Description
fp32_online_inference Runs online inference (batch_size=1).
fp32_batch_inference Runs batch inference (batch_size=100).
fp32_accuracy Measures the model accuracy (batch_size=100).

Docker

The model container includes the scripts and libraries needed to run MobileNet* v1 FP32 inference. To run one of the model inference quick start scripts using this container, you'll need to provide volume mounts for the ImageNet dataset and an output directory where checkpoint files will be written.

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

docker run \
  --env DATASET_DIR=${DATASET_DIR} \
  --env OUTPUT_DIR=${OUTPUT_DIR} \
  --env http_proxy=${http_proxy} \
  --env https_proxy=${https_proxy} \
  --volume ${DATASET_DIR}:${DATASET_DIR} \
  --volume ${OUTPUT_DIR}:${OUTPUT_DIR} \
  --privileged --init -t \
  intel/image-recognition:tf-latest-mobilenet-v1-fp32-inference \
  /bin/bash 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

MobileNet* V1 FP32 Inference TensorFlow* Model Package

View All Containers and Solutions 🡢

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.