This repository has been archived by the owner on Nov 17, 2023. It is now read-only.
Softsign op #9851
Merged
Softsign op #9851
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
does check_numeric_gradient() pass? |
|
yes it does pass the numeric_gradient check |
cjolivier01
approved these changes
Feb 22, 2018
anirudh2290
reviewed
Feb 22, 2018
| @@ -486,6 +486,20 @@ def fsigmoid(a): | |||
| check_symbolic_forward(y, [xa], [ya]) | |||
| check_symbolic_backward(y, [xa], [np.ones(shape)], [ya * (1 - ya)]) | |||
|
|
|||
| def test_softsign(): | |||
anirudh2290
approved these changes
Feb 22, 2018
dabraude
pushed a commit
to dabraude/incubator-mxnet
that referenced
this pull request
Feb 24, 2018
* Add SoftSign Activation function
dabraude
pushed a commit
to dabraude/incubator-mxnet
that referenced
this pull request
Feb 24, 2018
* Add SoftSign Activation function
| @@ -106,6 +106,23 @@ The storage type of ``sigmoid`` output is always dense | |||
|
|
|||
| MXNET_OPERATOR_REGISTER_BINARY_WITH_SPARSE_CPU(_backward_sigmoid, | |||
| unary_bwd<mshadow_op::sigmoid_grad>); | |||
| // softsign | |||
| MXNET_OPERATOR_REGISTER_UNARY(softsign) | |||
| MXNET_ADD_SPARSE_OP_ALIAS(softsign) | |||
There was a problem hiding this comment.
This operator doesn't have a sparse implementation. Sparse op alias should not be registered.
| @@ -168,6 +173,10 @@ void ActivationGradComputeImpl(const ActivationParam ¶m, const OpContext &ct | |||
| ActivationBackward<xpu, mshadow_op::softrelu, mshadow_op::softrelu_grad, DType>( | |||
| ctx, out_grad, out_data, req, output); | |||
| break; | |||
| case activation::kSoftSign: | |||
There was a problem hiding this comment.
Are you sure this is correct?
ActivationGradComputeImpl takes out_grad and out_data to calculate output. In another word,
for y = activation(x), it calculates dx = _backward_activation(dy, y), not dx = _backward_activation(dy, x).
| @@ -486,6 +486,21 @@ def fsigmoid(a): | |||
| check_symbolic_forward(y, [xa], [ya]) | |||
| check_symbolic_backward(y, [xa], [np.ones(shape)], [ya * (1 - ya)]) | |||
|
|
|||
| @with_seed() | |||
| def test_softsign(): | |||
There was a problem hiding this comment.
Is there unit test for Activation(act_type='softsign')???
rahul003
pushed a commit
to rahul003/mxnet
that referenced
this pull request
Jun 4, 2018
* Add SoftSign Activation function
zheng-da
pushed a commit
to zheng-da/incubator-mxnet
that referenced
this pull request
Jun 28, 2018
* Add SoftSign Activation function
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Add Softsign Activation function
Checklist
Essentials
make lint)Changes
Comments