README.md

MobileNet V1 Int8 inference

Description

This document has instructions for running MobileNet V1 Int8 inference using Intel-optimized TensorFlow.

Datasets

This step is required only for running accuracy, for running benchmark we do not need to provide dataset.

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 this directory when running MobileNet V1.

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=240).
int8_accuracy.sh	Measures the model accuracy (batch_size=100).
multi_instance_batch_inference.sh	A multi-instance run that uses all the cores for each socket for each instance with a batch size of 56. Uses synthetic data if no DATASET_DIR is set.
multi_instance_online_inference.sh	A multi-instance run that uses 4 cores per instance with a batch size of 1. Uses synthetic data if no DATASET_DIR is set.

Run the model

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: numactl wget Activate the tensorflow conda environment conda activate tensorflow	To run without AI Kit on Linux you will need: Python 3 intel-tensorflow>=2.5.0 git numactl wget A clone of the Model Zoo repo git clone /~https://github.com/IntelAI/models.git	To run without AI Kit on Windows you will need: Intel Model Zoo on Windows Systems prerequisites A clone of the Model Zoo repo git clone /~https://github.com/IntelAI/models.git

After finishing the setup above, download the pretrained model and set the PRETRAINED_MODEL environment var to the path to the frozen graph. If you run on Windows, please use a browser to download the pretrained model using the link below. For Linux, run:

wget https://storage.googleapis.com/intel-optimized-tensorflow/models/v1_8/mobilenetv1_int8_pretrained_model.pb
export PRETRAINED_MODEL=$(pwd)/mobilenetv1_int8_pretrained_model.pb

Intel® Neural Compressor int8 quantized MobileNet V1 pre-trained model is available as another option to download and try.

wget https://storage.googleapis.com/intel-optimized-tensorflow/intel-neural-compressor/v1_13/mobilenetv1-inc-int8-inference.pb
export PRETRAINED_MODEL=$(pwd)/mobilenetv1-inc-int8-inference.pb

Check the instructions for more details on how to quantize FP32 model using Intel® Neural Compressor.

Set environment variables for the path to your DATASET_DIR for ImageNet and an OUTPUT_DIR where log files will be written. Navigate to your model zoo directory and then run a quickstart script on either Linux or Windows.

Run on Linux:

# cd to your model zoo directory
cd models

export PRETRAINED_MODEL=<path to the frozen graph downloaded above>
export DATASET_DIR=<path to the ImageNet TF records>
export OUTPUT_DIR=<path to the directory where log files will be written>
# For a custom batch size, set env var `BATCH_SIZE` or it will run with a default value.
export BATCH_SIZE=<customized batch size value>

./quickstart/image_recognition/tensorflow/mobilenet_v1/inference/cpu/int8/<script name>.sh

Run on Windows

Using cmd.exe run:

# cd to your model zoo directory
cd models

set PRETRAINED_MODEL=<path to the frozen graph downloaded above>
set DATASET_DIR=<path to the ImageNet TF records>
set OUTPUT_DIR=<directory where log files will be written>
# For a custom batch size, set env var `BATCH_SIZE` or it will run with a default value.
set BATCH_SIZE=<customized batch size value>

bash quickstart\image_recognition\tensorflow\mobilenet_v1\inference\cpu\int8\<script name>.sh

Note: You may use cygpath to convert the Windows paths to Unix paths before setting the environment variables. As an example, if the dataset location on Windows is D:\user\ImageNet, convert the Windows path to Unix as shown:

cygpath D:\user\ImageNet
/d/user/ImageNet

Then, set the DATASET_DIR environment variable set DATASET_DIR=/d/user/ImageNet.

Additional Resources

• To run more advanced use cases, see the instructions here for calling the launch_benchmark.py script directly.
• To run the model using docker, please see the oneContainer workload container:
  https://software.intel.com/content/www/us/en/develop/articles/containers/mobilenetv1-int8-inference-tensorflow-container.html.