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 2018/12/23 10:30:56 UTC
[GitHub] yoel-shapiro commented on issue #13697: [MKLDNN] Enable signed int8
support for convolution.
yoel-shapiro commented on issue #13697: [MKLDNN] Enable signed int8 support for convolution.
URL: https://github.com/apache/incubator-mxnet/pull/13697#issuecomment-449627364
Hi, I'm still getting an issue when using "int8"
[I rebuilt MKLDNN, mxnet-incubator, and verified that the script works with "uint8"]
I am able to run calibration but when I use the quantized output model I get the following error, specifically when trying to read the model's predictions:
Traceback (most recent call last):
File "inference_dsalite.py", line 199, in <module>
image = pred[k_head][k_im].asnumpy()
File "/home/local/ANT/yoelsh/work/mxcode/incubator-mxnet/python/mxnet/ndarray/ndarray.py", line 1987, in asnumpy
ctypes.c_size_t(data.size)))
File "/home/local/ANT/yoelsh/work/mxcode/incubator-mxnet/python/mxnet/base.py", line 252, in check_call
raise MXNetError(py_str(_LIB.MXGetLastError()))
mxnet.base.MXNetError: [12:08:38] src/operator/subgraph/mkldnn/mkldnn_conv.cc:346: Can't handle negetive value for QuantizeData
I commented out the LOG(FATAL) line (#346), but then I get:
mxnet.base.MXNetError: [12:29:51] src/operator/nn/mkldnn/mkldnn_convolution.cc:140: Check failed: conv_pd.next_impl() No implementation
----------------------------------------------------------------
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