# Optimize a ResNet50* v1.5 FP32 Inference Model Package with TensorFlow*

Published: 01/05/2021

Last Updated: 06/15/2022

wget https://storage.googleapis.com/intel-optimized-tensorflow/models/v2_3_0/resnet50v1-5-fp32-inference.tar.gz

## Description

This document has instructions for running ResNet50* v1.5 FP32 inference using Intel® Optimization for TensorFlow*.

Note that the ImageNet dataset is used in these ResNet50 v1.5 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 TF 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=128).
fp32_accuracy Measures the model accuracy (batch_size=100).
multi_instance_batch_inference Uses numactl to run batch inference (batch_size=128) with one instance per socket for 1500 steps and 50 warm-up steps. If no DATASET_DIR is set, synthetic data is used. Waits for all instances to complete, then prints a summarized throughput value.
multi_instance_online_inference Uses numactl to run online inference (batch_size=1) using four cores per instance for 1500 steps and 50 warm-up steps. If no DATASET_DIR is set, synthetic data is used. Waits for all instances to complete, then prints a summarized throughput value.

#### Bare Metal

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

Download and untar the model package and then run a quick start script.

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

tar -xzf resnet50v1-5-fp32-inference.tar.gz
cd resnet50v1-5-fp32-inference

quickstart/<script name>.sh

## Documentation and Sources

Get Started​
Main GitHub*
Release Notes
Get Started Guide

Code Sources
Report Issue

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

ResNet50 V1.5 FP32 Inference TensorFlow* Container

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.