This article will describe performance considerations for CPU inference using Intel® Optimization for TensorFlow*
This paper demonstrates a special version of Caffe* — a deep learning framework originally developed by the Berkeley Vision and Learning Center (BVLC) — that is optimized for Intel® architecture.
The computer learning code Caffe* has been optimized for Intel® Xeon Phi™ processors. This article provides detailed instructions on how to compile and run this Caffe* optimized for Intel® architecture to obtain the best performance on Intel Xeon Phi processors.
Get recipes for installing development tools and libraries on various platforms for the Python library.
On November 7, 2017, UC Berkeley, U-Texas, and UC Davis researchers published their results training ResNet-50* in a record time (as of the time of their publication) of 31 minutes and AlexNet* in a record time of 11 minutes on CPUs to state-of-the-art accuracy. These results were obtained on Intel® Xeon® Scalable processors (formerly codename Skylake-SP).