BTW, could we upload our model/parameters into http://data.mxnet.io/data/ so 
that the end user could reproduce the INT8 performance and accuracy w/o 
training the model again?

[ Full content available at: 
https://github.com/apache/incubator-mxnet/pull/12530 ]
This message was relayed via gitbox.apache.org for [email protected]

Reply via email to