tencent cloud

lscpu | grep "Core(s) per socket" | cut -d':' -f2 | xargs

 export OMP_NUM_THREADS= # <physicalcores>
 export KMP_AFFINITY="granularity=fine,verbose,compact,1,0"
 export KMP_BLOCKTIME=1
 export KMP_SETTINGS=1
 export TF_NUM_INTRAOP_THREADS= # <physicalcores>
 export TF_NUM_INTEROP_THREADS=1
 export TF_ENABLE_MKL_NATIVE_FORMAT=0

import os
os.environ["KMP_BLOCKTIME"] = "1"
os.environ["KMP_SETTINGS"] = "1"
os.environ["KMP_AFFINITY"]= "granularity=fine,verbose,compact,1,0"
if FLAGS.num_intra_threads > 0:
 os.environ["OMP_NUM_THREADS"]= # <physical cores>
os.environ["TF_ENABLE_MKL_NATIVE_FORMAT"] = "0"
config = tf.ConfigProto()
config.intra_op_parallelism_threads = # <physical cores>
config.inter_op_parallelism_threads = 1
tf.Session(config=config)

lscpu | grep "Core(s) per socket" | cut -d':' -f2 | xargs

export OMP_NUM_THREADS=physicalcores
export GOMP_CPU_AFFINITY="0-<physicalcores-1>"
export OMP_SCHEDULE=STATIC
export OMP_PROC_BIND=CLOSE

export OMP_NUM_THREADS=physicalcores
export LD_PRELOAD=<path_to_libiomp5.so>
export KMP_AFFINITY="granularity=fine,verbose,compact,1,0"
export KMP_BLOCKTIME=1
export KMP_SETTINGS=1

import intel_pytorch_extension
...
net = net.to('xpu')       # Move model to IPEX format
data = data.to('xpu')     # Move data  to IPEX format
...
output = net(data)        # Perform inference with IPEX
output = output.to('cpu') # Move output back to ATen format

conda create -n lpot python=3.7
conda activate lpot

pip install lpot

 git clone https://github.com/intel/lpot.git
 cd lpot
 pip install –r requirements.txt
 python setup.py install

mkdir –p img_raw/val && cd img_raw
wget http://www.image-net.org/challenges/LSVRC/2012/dd31405981
ef5f776aa17412e1f0c112/ILSVRC2012_img_val.tar
tar –xvf ILSVRC2012_img_val.tar -C val

cd val
wget -qO -https://raw.githubusercontent.com/soumith/
imagenetloader.torch/master/valprep.sh | bash

cd examples/tensorflow/image_recognition
bash prepare_dataset.sh --output_dir=./data --raw_dir=/PATH/TO/img_raw/val/ 
--subset=validation

wget https://storage.googleapis.com/intel-optimized-tensorflow/
 models/v1_6/resnet50_fp32_pretrained_model.pb

cd examples/tensorflow/image_recognition
bash run_tuning.sh --config=resnet50_v1.yaml \\
--input_model=/PATH/TO/resnet50_fp32_pretrained_model.pb \\
--output_model=./lpot_resnet50_v1.pb

bash run_benchmark.sh --input_model=./lpot_resnet50_v1.pb
--config=resnet50_v1.yaml

 accuracy mode benchmarkresult:
 Accuracy is 0.739
 Batch size = 32
 Latency: 1.341 ms
 Throughput: 745.631 images/sec
 performance mode benchmark result:
 Accuracy is 0.000
 Batch size = 32
 Latency: 1.300 ms
 Throughput: 769.302 images/sec