Skip to content
This repository has been archived by the owner on Nov 17, 2023. It is now read-only.

[R] An easy-to-use interface for mlp training #460

Merged
merged 6 commits into from
Nov 2, 2015
Merged

[R] An easy-to-use interface for mlp training #460

merged 6 commits into from
Nov 2, 2015

Conversation

hetong007
Copy link
Contributor

For mlp, the symbolic connection can be built automatically. The "5 minutes" tutorials will be updated with this interface soon.

if (out_activation == "rmse") {
out <- mx.symbol.LinearRegressionOutput(fc)
} else if (out_activation == "softmax") {
out <- mx.symbol.Softmax(fc)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

use SoftmaxOutput instead of Softmax, c.f. #434

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Seems SoftmaxOutput hasn't been defined yet, I got "could not find function "mx.symbol.SoftmaxOutput""

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Need to make the latest mxnet and do make rcppexport

hetong007 added a commit that referenced this pull request Nov 2, 2015
[R] An easy-to-use interface for mlp training
@hetong007 hetong007 merged commit b1c7e69 into apache:master Nov 2, 2015
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants