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_r251822255
##########
File path: python/mxnet/contrib/quantization.py
##########
@@ -80,8 +80,7 @@ def _quantize_params(qsym, params, th_dict):
quantized_params[name] = ndarray.array([th_dict[output][1]])
return quantized_params
-def _quantize_symbol(sym, excluded_symbols=None, offline_params=None,
- quantized_dtype='int8', calib_quantize_op=False):
+def _quantize_symbol(sym, excluded_symbols=None, offline_params=None,
quantized_dtype='int8'):
Review comment:
Oh, Just found _contrib_quantize_v2 used `auto` as default out_type. To keep
consistent with this, change that op to use `int8` as default.
----------------------------------------------------------------
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
