Hi,
How to do float16 or int8 quantization of gluoncv models?
I’m specifically interested in resnets, inceptionV3, mobilenet
Have you ever looked into this post: https://medium.com/apache-mxnet/model-quantization-for-production-level-neural-network-inference-f54462ebba05?
yes at first look I didn’t find what I was looking but it helped me find other things that were helpful such as https://github.com/apache/incubator-mxnet/tree/master/example/quantization and https://gluon-cv.mxnet.io/build/examples_deployment/int8_inference.html