This document has instructions for running SSD-ResNet34 FP32 inference using Intel-optimized TensorFlow.
The SSD-ResNet34 accuracy scripts (fp32_accuracy.sh and fp32_accuracy_1200.sh) 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.sh and fp32_inference_1200.sh) use synthetic data, so no dataset is required.
| Script name | Description |
|---|---|
| fp32_accuracy_1200.sh | Runs an accuracy test using data in the TF records format with an input size of 1200x1200. |
| fp32_accuracy.sh | Runs an accuracy test using data in the TF records format with an input size of 300x300. |
| fp32_inference_1200.sh | 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. |
| fp32_inference.sh | 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. |
| multi_instance_batch_inference_1200.sh | 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.sh | 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. |
Setup your environment using the instructions below, depending on if you are using AI Kit:
| Setup using AI Kit on Linux | Setup without AI Kit on Linux | Setup without AI Kit on Windows |
|---|---|---|
|
To run using AI Kit on Linux you will need:
|
To run without AI Kit on Linux you will need:
|
To run without AI Kit on Windows you will need:
|
The TensorFlow models and
benchmarks repos are used by
SSD-ResNet34 FP32 inference. Clone those at the git SHAs specified
below and set the TF_MODELS_DIR environment variable to point to the
directory where the models repo was cloned.
git clone --single-branch https://github.com/tensorflow/models.git tf_models
git clone --single-branch https://github.com/tensorflow/benchmarks.git ssd-resnet-benchmarks
cd tf_models
export TF_MODELS_DIR=$(pwd)
git checkout f505cecde2d8ebf6fe15f40fb8bc350b2b1ed5dc
cd ../ssd-resnet-benchmarks
git checkout 509b9d288937216ca7069f31cfb22aaa7db6a4a7
cd ..
Download the SSD-ResNet34 pretrained model for either the 300x300 or 1200x1200
input size, depending on which quickstart script you are
going to run. Set the PRETRAINED_MODEL environment variable for the path to the
pretrained model that you'll be using.
If you run on Windows, please use a browser to download the pretrained model using the link below.
For Linux, run:
# ssd-resnet34 300x300
wget https://storage.googleapis.com/intel-optimized-tensorflow/models/v1_8/ssd_resnet34_fp32_bs1_pretrained_model.pb
export PRETRAINED_MODEL=$(pwd)/ssd_resnet34_fp32_bs1_pretrained_model.pb
# ssd-resnet34 1200x1200
wget https://storage.googleapis.com/intel-optimized-tensorflow/models/v1_8/ssd_resnet34_fp32_1200x1200_pretrained_model.pb
export PRETRAINED_MODEL=$(pwd)/ssd_resnet34_fp32_1200x1200_pretrained_model.pb
After installing the prerequisites and cloning the models and benchmarks
repos, and downloading the pretrained model, set the required environment
variables. Set an environment variable for the path to an OUTPUT_DIR
where log files will be written. If the accuracy test is being run, then
also set the DATASET_DIR to point to the folder where the COCO dataset
validation-00000-of-00001 file is located. Once the environment variables
are set, you can then run a quickstart script from the
Model Zoo on either Linux or Windows.
# cd to your model zoo directory
cd models
# set environment variables
export DATASET_DIR=<directory with the validation-*-of-* files (for accuracy testing only)>
export TF_MODELS_DIR=<path to the TensorFlow Models repo>
export PRETRAINED_MODEL=<path to the 300x300 or 1200x1200 pretrained model pb file>
export OUTPUT_DIR=<directory where log files will be written>
./quickstart/object_detection/tensorflow/ssd-resnet34/inference/cpu/fp32/<script name>.sh
Using cmd.exe, run:
# cd to your model zoo directory
cd models
set PRETRAINED_MODEL=<path to the 300x300 or 1200x1200 pretrained model pb file>
set DATASET_DIR=<directory with the validation-*-of-* files (for accuracy testing only)>
set OUTPUT_DIR=<directory where log files will be written>
set TF_MODELS_DIR=<path to the TensorFlow Models repo>
bash quickstart\object_detection\tensorflow\ssd-resnet34\inference\cpu\fp32\<script name>.sh
Note: You may use
cygpathto convert the Windows paths to Unix paths before setting the environment variables. As an example, if the dataset location on Windows isD:\user\coco_dataset, convert the Windows path to Unix as shown:cygpath D:\user\coco_dataset /d/user/coco_datasetThen, set the
DATASET_DIRenvironment variableset DATASET_DIR=/d/user/coco_dataset.
- To run more advanced use cases, see the instructions here
for calling the
launch_benchmark.pyscript directly. - To run the model using docker, please see the oneContainer
workload container:
https://software.intel.com/content/www/us/en/develop/articles/containers/ssd-resnet34-fp32-inference-tensorflow-container.html.