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 2019/06/11 21:27:22 UTC
[GitHub] [incubator-mxnet] ThomasDelteil commented on issue #11756:
[MXNET-677] int8 quantization does not work on toy mnist dataset
ThomasDelteil commented on issue #11756: [MXNET-677] int8 quantization does not work on toy mnist dataset
URL: https://github.com/apache/incubator-mxnet/issues/11756#issuecomment-501029690
@xinyu-intel @PatricZhao is there work to support `int8` type in MKLDNN ? Currently it only supports `uint8`
```text
MXNetError: [21:24:54] src/operator/quantization/mkldnn/mkldnn_quantized_conv.cc:41: Check failed: in_data[0].dtype() == mshadow::kUint8 (5 vs. 3) : mkldnn_quantized_conv op only supports uint8 as input type
```
----------------------------------------------------------------
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:
users@infra.apache.org
With regards,
Apache Git Services