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

Update parameter documentation for TransposedConv2D #283

Merged
merged 3 commits into from
Jun 23, 2019
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 7 additions & 4 deletions Sources/TensorFlow/Layers/Convolutional.swift
Original file line number Diff line number Diff line change
Expand Up @@ -417,8 +417,9 @@ public struct TransposedConv2D: Layer {
/// activation function, strides, and padding.
///
/// - Parameters:
/// - filter: The 4-D convolution kernel.
/// - bias: The bias vector.
/// - filter: A 4-D tensor of shape
/// `[width, height, input channel count, output channel count]`.
/// - bias: The bias tensor of shape `[output channel count]`.
/// - activation: The element-wise activation function.
/// - strides: The strides of the sliding window for spatial dimensions.
/// - padding: The padding algorithm for convolution.
Expand Down Expand Up @@ -465,7 +466,8 @@ public extension TransposedConv2D {
/// initialization with the specified generator. The bias vector is initialized with zeros.
///
/// - Parameters:
/// - filterShape: The shape of the 4-D convolution kernel.
/// - filterShape: A 4-D tensor of shape
/// `[width, height, input channel count, output channel count]`.
/// - strides: The strides of the sliding window for spatial dimensions.
/// - padding: The padding algorithm for convolution.
/// - activation: The element-wise activation function.
Expand Down Expand Up @@ -497,7 +499,8 @@ public extension TransposedConv2D {
/// initialization with the specified seed. The bias vector is initialized with zeros.
///
/// - Parameters:
/// - filterShape: The shape of the 4-D convolution kernel.
/// - filterShape: A 4-D tensor of shape
/// `[width, height, input channel count, output channel count]`.
/// - strides: The strides of the sliding window for spatial dimensions.
/// - padding: The padding algorithm for convolution.
/// - activation: The element-wise activation function.
Expand Down