pengzhao-intel commented on issue #13657: update with release notes for 1.4.0 release URL: https://github.com/apache/incubator-mxnet/pull/13657#issuecomment-447778183 @srochel could you help add the below description into the new feature parts of r1.4? @larroy @aaronmarkham could you help take a reveiw for the contents? Thanks in advance. -------------------------------------------------------------------------------------------------------------- **MKDNN backend: Graph optimization and Quantization (experimental)** Two advanced features, graph optimization (operator fusion) and reduced-precision (INT8) computation, are introduced to MKL-DNN backend in this release (#12530, #13297, #13260). These features significantly boost the inference performance on CPU (up to 4X) for a broad range of deep learning topologies. - Graph Optimization MKL-DNN backend takes advantage of MXNet subgraph to implement the most of possible operator fusions for inference, such as Convolution + ReLU, Batch Normalization folding, etc. When using mxnet-mkl package, users can easily enable this feature by setting `export MXNET_SUBGRAPH_BACKEND=MKLDNN`. - Quantization Performance of reduced-precision (INT8) computation is also dramatically improved after the graph optimization feature is applied on CPU Platforms. Various models are supported and can benefit from reduced-precision computation, including symbolic models, Gluon models and even custom models. Users can run most of pre-trained models with only few lines of command and a new quantization script `imagenet_gen_qsym_mkldnn.py`. The observed accuracy loss is less than 0.5% for popular CNN networks, like ResNet-50, Inception-BN, MobileNet, etc. Please find detailed information and performance/accuracy numbers here: [MKLDNN README](https://github.com/apache/incubator-mxnet/blob/master/MKLDNN_README.md), [quantization README](https://github.com/apache/incubator-mxnet/tree/master/example/quantization#1) and [design proposal](https://cwiki.apache.org/confluence/display/MXNET/MXNet+Graph+Optimization+and+Quantization+based+on+subgraph+and+MKL-DNN)
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
