You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2019/02/12 07:24:02 UTC
[GitHub] eric-haibin-lin opened a new issue #14126: Safe accumulation type
for nd.norm
eric-haibin-lin opened a new issue #14126: Safe accumulation type for nd.norm
URL: https://github.com/apache/incubator-mxnet/issues/14126
For FP16, reduction operators tend to loss precision if the accumulation data type remains fp16. Instead, the accumulation dtype should be in fp32. i.e.
```
dtype = fp16 -> acc_type = fp32
dtype = fp32 -> acc_type = fp64
dtype = fp64 -> acc_type = fp64
```
We should do it for the norm op.
Reference impl for softmax: https://github.com/apache/incubator-mxnet/pull/14098
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services