Highly Efficient 8-bit Low Precision Inference of Convolutional Neural Networks with IntelCaffe

Jiong Gong, Haihao Shen, Guoming Zhang, Xiaoli Liu, Shane Li, Ge Jin, Niharika Maheshwari, Evarist Fomenko, Eden Segal
Intel Corporation
arXiv:1805.08691 [cs.CV], (4 May 2018)


   title={Highly Efficient 8-bit Low Precision Inference of Convolutional Neural Networks with IntelCaffe},

   author={Gong, Jiong and Shen, Haihao and Zhang, Guoming and Liu, Xiaoli and Li, Shane and Jin, Ge and Maheshwari, Niharika and Fomenko, Evarist and Segal, Eden},






Download Download (PDF)   View View   Source Source   Source codes Source codes




High throughput and low latency inference of deep neural networks are critical for the deployment of deep learning applications. This paper presents the efficient inference techniques of IntelCaffe, the first Intel optimized deep learning framework that supports efficient 8-bit low precision inference and model optimization techniques of convolutional neural networks on Intel Xeon Scalable Processors. The 8-bit optimized model is automatically generated with a calibration process from FP32 model without the need of fine-tuning or retraining. We show that the inference throughput and latency with ResNet-50, Inception-v3 and SSD are improved by 1.38X-2.9X and 1.35X-3X respectively with neglectable accuracy loss from IntelCaffe FP32 baseline and by 56X-75X and 26X-37X from BVLC Caffe. All these techniques have been open-sourced on IntelCaffe GitHub1, and the artifact is provided to reproduce the result on Amazon AWS Cloud.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: