CompressionΒΆ
The following tutorials will help you learn how to use compression techniques with MXNet.
Compression: float16https://mxnet.incubator.apache.org/versions/master/faq/float16.html
How to use float16 in your model to boost training speed.
Gradient Compressionhttps://mxnet.incubator.apache.org/versions/master/faq/gradient_compression.html
How to use gradient compression to reduce communication bandwidth and increase speed.
Inference with Quantized Modelshttps://gluon-cv.mxnet.io/build/examples_deployment/int8_inference.html
How to use quantized GluonCV models for inference on Intel Xeon Processors to gain higher performance.