ZhennanQin commented on a change in pull request #13697: [MKLDNN] Enable signed
int8 support for convolution.
URL: https://github.com/apache/incubator-mxnet/pull/13697#discussion_r251822762
##########
File path: src/operator/quantization/mkldnn/mkldnn_dequantize-inl.h
##########
@@ -74,6 +74,9 @@ static void MKLDNNDequantizeComputeKer(const
std::vector<NDArray> &inputs,
i_dims[i] = static_cast<int>(in_buffer.shape()[i]);
}
mkldnn::memory::format i_fmt =
static_cast<mkldnn::memory::format>(i_desc.data.format);
+ if (i_fmt == mkldnn::memory::format::nhwc) {
+ i_fmt = mkldnn::memory::format::nchw;
Review comment:
Done.
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
