Convolution and Deconvolution.See: Description
| Class | Description |
|---|---|
| Conv1d |
A
Conv1d layer works similar to Convolution layer with the exception of the
number of dimension it operates on being only one, which is LayoutType.WIDTH. |
| Conv1d.Builder | |
| Conv1dTranspose |
A
Conv1dTranspose layer works similar to Deconvolution layer with the exception
of the number of dimension it operates on being only one, which is LayoutType.WIDTH. |
| Conv1dTranspose.Builder |
The Builder to construct a
Conv1dTranspose type of Block. |
| Conv2d |
Being the pioneer of convolution layers,
Conv2d layer works on two dimensions of input,
LayoutType.WIDTH and LayoutType.HEIGHT as usually a Conv2d layer is used
to process data with two spatial dimensions, namely image. |
| Conv2d.Builder | |
| Conv2dTranspose | |
| Conv2dTranspose.Builder |
The Builder to construct a
Conv2dTranspose type of Block. |
| Conv3d |
Conv3d layer behaves just as Convolution does, with the distinction being it
operates of 3-dimensional data such as medical images or video data. |
| Conv3d.Builder | |
| Convolution |
A convolution layer does a dot product calculation on each channel of \(k\)-channel input data by
specified number of filters, each containing \(k\) kernels for calculating each channel in the
input data and then summed per filter, hence the number of filters denote the number of output
channels of a convolution layer.
|
| Convolution.ConvolutionBuilder<T extends Convolution.ConvolutionBuilder> |
A builder that can build any
Convolution block. |
| Deconvolution |
Transposed convolution, also named fractionally-strided convolution Dumoulin & Visin or deconvolution Long et al., 2015, serves this purpose.
|
| Deconvolution.DeconvolutionBuilder<T extends Deconvolution.DeconvolutionBuilder> |
A builder that can build any
Deconvolution block. |
Convolution and Deconvolution.