This document has instructions for running MobileNet V2 inference using Intel-optimized 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 MobileNet V1.
Script name | Description |
---|---|
inference.sh |
Runs realtime inference using a default batch_size=1 for the specified precision (int8, fp32, bfloat16). To run inference for throughtput, set BATCH_SIZE environment variable. |
inference_realtime_multi_instance.sh |
A multi-instance run that uses 4 cores per instance with batch_size=1 for the specified precision (fp32, int8, bfloat16, bfloat32). Uses synthetic data if no DATASET_DIR is set |
inference_throughput_multi_instance.sh |
A multi-instance run that uses 4 cores per instance with batch_size=448 for the specified precision (fp32, int8, bfloat16, bfloat32). Uses synthetic data if no DATASET_DIR is set |
accuracy.sh |
Measures the model accuracy (batch_size=100) for the specified precision (fp32, int8, bfloat16, bfloat32). |
Setup your environment using the instructions below, depending on if you are using AI Tools:
Setup using AI Tools on Linux | Setup without AI Tools on Linux | Setup without AI Tools on Windows |
---|---|---|
To run using AI Tools on Linux you will need:
|
To run without AI Tools on Linux you will need:
|
To run without AI Tools on Windows you will need:
|
After finishing the setup above, download the pretrained model based on PRECISION
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:
# FP32, BFloat16 and BFloat32 Pretrained model:
wget https://storage.googleapis.com/mobilenet_v2/checkpoints/mobilenet_v2_1.4_224.tgz
tar -xvzf mobilenet_v2_1.4_224.tgz
export PRETRAINED_MODEL=$(pwd)/mobilenet_v2_1.4_224_frozen.pb
Intel® Neural Compressor int8 quantized MobileNet V2 pre-trained model:
wget https://storage.googleapis.com/intel-optimized-tensorflow/models/2_11_0/mobilenetv2_inc_int8.pb
export PRETRAINED_MODEL=$(pwd)/mobilenetv2_inc_int8.pb
Set the environment variables and run quickstart script on either Linux or Windows systems. See the list of quickstart scripts for details on the different options.
# cd to your AI Reference Models directory
cd models
export PRETRAINED_MODEL=<path to the frozen graph downloaded above>
export DATASET_DIR=<path to the ImageNet TF records>
export PRECISION=<set the precision to "int8" or "fp32" or "bfloat16" or "bfloat32">
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_v2/inference/cpu/<script name>.sh
Using cmd.exe
run:
# cd to your AI Reference Models directory
cd models
set PRETRAINED_MODEL=<path to the frozen graph downloaded above>
set DATASET_DIR=<path to the ImageNet TF records>
set PRECISION=<set the precision to "int8" or "fp32">
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>
# Run a quick start script for inference or accuracy
bash quickstart\image_recognition\tensorflow\mobilenet_v2\inference\cpu\<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 isD:\user\ImageNet
, convert the Windows path to Unix as shown:cygpath D:\user\ImageNet /d/user/ImageNet
Then, set the
DATASET_DIR
environment variableset DATASET_DIR=/d/user/ImageNet
.