TaoLv commented on a change in pull request #17161: [MKL-DNN] Enhance
Quantization Method
URL: https://github.com/apache/incubator-mxnet/pull/17161#discussion_r361321307
##########
File path: python/mxnet/contrib/quantization.py
##########
@@ -627,8 +631,9 @@ def quantize_model_mkldnn(sym, arg_params, aux_params,
return qsym, qarg_params, aux_params
def quantize_graph(sym, arg_params, aux_params, ctx=cpu(),
- excluded_sym_names=None, excluded_op_names=None,
calib_mode='entropy',
- quantized_dtype='int8', quantize_mode='full', logger=None):
+ excluded_sym_names=None, excluded_op_names=None,
+ calib_mode='entropy', quantized_dtype='int8',
quantize_mode='full',
+ LayerOutputCollector=None, logger=None):
Review comment:
Is this an API breaking change? Will it affect other users applications?
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
