ConvTranspose1D

1-dimensional (temporal) transposed convolution, also called deconvolution.

This node can be thought of as an inverse to a Conv1D, but it is not really a true inverse. In Conv1D, we slide a 1D moving window across the input and compute a single weighted output for each window position. Here, we slide across the input one position at a time and compute a 1D moving window of weighted values, and add a bias to that.

The only supported input data type is Float32, and the input must have at least 2 dimensions. The output will have the same data type as the input.

By clicking the node the following parameters can be configured on the right panel:

• Filters: Number of convolutions to perform. This will be se size of the first dimension in the output.
• Kernel size: The size of the moving window.
• Stride: Number of places to move the moving window after each computation.
• Dilation: Gap between each position in the kernel.
• Use bias: If true, a learnable parameter of shape (<Filters>) is added to the output after the convolution is done.
• Padding: Zero-padding to add to both sides of the input.
• Output padding: Size to add to one side of the output.
• Number of connections: Increases the number of connections on this node. The first input will lead to the first output, the second input to the second output and so on. This is useful because even though the connections are separate they share the same weight and bias.
• Weight initializer: Initial value for the weight.
• Bias initializer: Initial value for the bias.