Skip to content
This repository has been archived by the owner on Jul 1, 2023. It is now read-only.

Adding GlobalAveragePooling 3D #72

Merged
merged 2 commits into from
Apr 2, 2019
Merged

Adding GlobalAveragePooling 3D #72

merged 2 commits into from
Apr 2, 2019

Conversation

Shashi456
Copy link
Contributor

No description provided.

@rxwei rxwei self-requested a review April 2, 2019 11:01
Copy link
Contributor

@rxwei rxwei left a comment

Choose a reason for hiding this comment

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

@@ -1022,7 +1022,7 @@ public struct GlobalAveragePooling1D<Scalar: TensorFlowFloatingPoint>: Layer {
/// - input: The input to the layer.
/// - context: The contextual information for the layer application, e.g. the current learning
/// phase.
/// - Returns: The output
/// - Returns: The output
Copy link
Contributor

Choose a reason for hiding this comment

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

Add period.

Suggested change
/// - Returns: The output
/// - Returns: The output.

/// - input: The input to the layer.
/// - context: The contextual information for the layer application, e.g. the current learning
/// phase.
/// - Returns: The output
Copy link
Contributor

Choose a reason for hiding this comment

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

Add period.

/// - Returns: The output
@differentiable
public func applied(to input: Tensor<Scalar>, in _: Context) -> Tensor<Scalar> {
return input.mean(alongAxes: [1,2,3]).reshaped(to: [input.shape[0], input.shape[4]])
Copy link
Contributor

Choose a reason for hiding this comment

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

Add a space after each comma.

Suggested change
return input.mean(alongAxes: [1,2,3]).reshaped(to: [input.shape[0], input.shape[4]])
return input.mean(alongAxes: [1, 2, 3]).reshaped(to: [input.shape[0], input.shape[4]])

@Shashi456
Copy link
Contributor Author

@rxwei is it okay if i add the tests in another PR? I think most of the conv layers lack a test, So i'll go through them one by one?

@rxwei
Copy link
Contributor

rxwei commented Apr 2, 2019

Sure. Sounds good.

@rxwei rxwei merged commit efaa6d0 into tensorflow:master Apr 2, 2019
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