anirudh2290 commented on issue #15118: Conversion from FP32 model to Mixed Precision model URL: https://github.com/apache/incubator-mxnet/pull/15118#issuecomment-501348376 @samskalicky the conversion itself will work but the inference is likely not to work because operator support for FP16 not being great on CPU. Thanks for pointing though, I should still add a conversion test for convert_hybrid_block for cpu.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to 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
