ResNet50v1.5 Int8 Inference Tensorflow* Container

Pull Command

docker pull intel/image-recognition:tf-2.4.0-resnet50v1-5-int8-inference

Description

This document has instructions for running ResNet50 v1.5 Int8 inference using Intel® Optimizations for TensorFlow*.

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.

Set the DATASET_DIR to point to the TF records directory when running ResNet50 v1.5.

Quick Start Scripts

Script name Description
int8_online_inference.sh Runs online inference (batch_size=1).
int8_batch_inference.sh Runs batch inference (batch_size=128).
int8_accuracy.sh Measures the model accuracy (batch_size=100).
multi_instance_batch_inference.sh Uses numactl to run batch inference (batch_size=128) with one instance per socket for 1500 steps and 50 warmup steps. If no DATASET_DIR is set, synthetic data is used. The script waits for all instances to complete, then prints a summarized throughput value.
multi_instance_online_inference.sh Uses numactl to run online inference (batch_size=1) using four cores per instance for 1500 steps and 50 warmup steps. If no DATASET_DIR is set, synthetic data is used. The script waits for all instances to complete, then prints a summarized throughput value.

Docker

The model container includes the scripts and libraries needed to run ResNet50 v1.5 Int8 inference. To run one of the quickstart scripts using this container, you'll need to provide volume mounts for the dataset and an output directory.

For accuracy, DATASET_DIR is required to be set. For inference, just to evaluate performance on synthetic data, the DATASET_DIR is not needed. Otherwise DATASET_DIR needs to be set. Add or remove DATASET_DIR environment variable and volume mount accordingly in following command:

DATASET_DIR=<path to the 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-2.4.0-resnet50v1-5-int8-inference \
  /bin/bash quickstart/<script name>.sh

Documentation and Sources

Get Started​
Docker Repo
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

ResNet50v1.5 Int8 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.