larroy commented on a change in pull request #15331: [fix] missing input log
higher order.
URL: https://github.com/apache/incubator-mxnet/pull/15331#discussion_r307541582
##########
File path: src/operator/tensor/elemwise_unary_op_basic.cc
##########
@@ -1117,15 +1117,15 @@
MXNET_OPERATOR_REGISTER_BINARY_WITH_SPARSE_CPU_DR(_backward_log10,
unary_bwd<mshadow_op::log10_grad>)
.set_attr<nnvm::FGradient>("FGradient",
[](const nnvm::NodePtr& n, const std::vector<nnvm::NodeEntry>& ograds) {
- // ograds[0]: dL/dxgrad
+ // ograds[0]: dL/dygrad
Review comment:
I think the notation is complicating us in excess as it gets pretty hairy.
It's the head gradient of the previous (output) node, which has shape of x, and
x_grad. So it has to be related to x, not y.
I think in Lagrange notation it would be $F_{L_x}$
----------------------------------------------------------------
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
