Run ResNet-34* SSD FP32 Inference for a TensorFlow* Container

Published: 10/23/2020  

Last Updated: 06/15/2022

Pull Command

docker pull intel/object-detection:tf-latest-ssd-resnet34-fp32-inference

Description

This document has instructions for running ResNet34* SSD FP32 inference using Intel® Optimization for TensorFlow*.

The ResNet34 SSD accuracy scripts (fp32_accuracy and fp32_accuracy_1200) use the COCO validation dataset in the TF records format. See the COCO dataset document for instructions on downloading and preprocessing the COCO validation dataset.

The performance benchmarking scripts (fp32_inference and fp32_inference_1200) use synthetic data, so no dataset is required.

Quick Start Scripts

Script name Description
fp32_accuracy Runs an accuracy test using data in the TF records format with an input size of 300x300.
fp32_accuracy_1200 Runs an accuracy test using data in the TF records format with an input size of 1200x1200.
fp32_inference Runs inference with a batch size of 1 using synthetic data with an input size of 300x300. Prints out the time spent per batch and total samples/second.
fp32_inference_1200 Runs inference with a batch size of 1 using synthetic data with an input size of 1200x1200. Prints out the time spent per batch and total samples/second.
multi_instance_batch_inference_1200 Uses numactl to run inference (batch_size=1) with one instance per socket. Uses synthetic data with an input size of 1200x1200. Waits for all instances to complete, then prints a summarized throughput value.
multi_instance_online_inference_1200 Uses numactl to run inference (batch_size=1) with 4 cores per instance. Uses synthetic data with an input size of 1200x1200. Waits for all instances to complete, then prints a summarized throughput value.


Docker*

The model container includes the scripts and libraries needed to run ResNet34 SSD FP32 inference. To run one of the quick start scripts using this container, you'll need to provide a volume mount for the output directory. Running an accuracy test will also require a volume mount for the dataset directory (with the COCO validation dataset in the TF records format). Inference performance scripts use synthetic data.

DATASET_DIR=<path to the dataset (for accuracy testing only)>
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/object-detection:tf-latest-ssd-resnet34-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

ResNet34 SSD 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.