zheng-da commented on a change in pull request #10433: [MXNET-290] MKLDNN
support for model quantization
URL: https://github.com/apache/incubator-mxnet/pull/10433#discussion_r183167546
##########
File path: src/operator/quantization/quantize_graph_pass.cc
##########
@@ -198,7 +198,7 @@ Graph QuantizeGraph(Graph &&src) {
NodePtr mirror_node = mirror_map.at(e.node.get());
NodeEntry mirror_entry = NodeEntry{
mirror_node, e.index, e.version};
- size_t num_outputs = e.node->num_outputs();
+ size_t num_outputs = mirror_node->num_outputs() - 2;
Review comment:
but it looks to me that this change applies to all operators, not just
pooling.
also, why 2? if one of the output is workspace, shouldn't it be 1?
----------------------------------------------------------------
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:
us...@infra.apache.org
With regards,
Apache Git Services
