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 2019/08/26 02:23:57 UTC
[GitHub] [incubator-mxnet] ElaineBao commented on a change in pull request
#16003: add uint8 bn mkldnn implementation
ElaineBao commented on a change in pull request #16003: add uint8 bn mkldnn implementation
URL: https://github.com/apache/incubator-mxnet/pull/16003#discussion_r317432365
##########
File path: example/quantization/imagenet_gen_qsym_mkldnn.py
##########
@@ -216,7 +216,7 @@ def save_params(fname, arg_params, aux_params, logger=None):
if exclude_first_conv:
excluded_sym_names += ['resnetv10_conv0_fwd']
elif args.model.find('resnet') != -1 and args.model.find('v2') != -1:
- excluded_sym_names += ['resnetv20_flatten0_flatten0']
+ excluded_sym_names += ['resnetv20_flatten0_flatten0', 'resnetv20_stage1_batchnorm0_fwd']
Review comment:
This is for the sake of accuracy, if do not exclude this layer, top-1 accuracy will drop to 52.3. Reason of this accuracy drop is under investigation.
----------------------------------------------------------------
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:
users@infra.apache.org
With regards,
Apache Git Services