TaoLv 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_r244152277
##########
File path: example/quantization/imagenet_gen_qsym_mkldnn.py
##########
@@ -302,9 +294,8 @@ def save_params(fname, arg_params, aux_params,
logger=None):
ctx=ctx,
excluded_sym_names=excluded_sym_names,
calib_mode=calib_mode,
calib_data=data,
num_calib_examples=num_calib_batches * batch_size,
-
calib_layer=calib_layer, quantized_dtype=args.quantized_dtype,
-
label_names=(label_name,), calib_quantize_op = True,
- logger=logger)
+ calib_layer=None,
quantized_dtype=args.quantized_dtype,
Review comment:
calib_layer is removed?
----------------------------------------------------------------
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
