Base class for convolutional layers.
1D convolution for structured image-like inputs.
2D convolution for structured image-like inputs.
2D convolution for structured image-like inputs. Input should have three dimensions: height (number of rows), width (number of columns), and number of channels. Convolution is over height and width.
3D convolution for structured image-like inputs.
3D convolution for structured image-like inputs. Input should have four dimensions: depth, height, width and number of channels. Convolution is over depth, height and width. For simplicity we assume NDHWC data format, i.e. channels last.
1D cropping layer
2D cropping layer
3D cropping layer
Base upsampling layer
1D upsampling layer
2D upsampling layer
3D upsampling layer
1D zero padding layer
2D zero padding layer
3D zero padding layer
1D convolution for structured image-like inputs. Input should have two dimensions: height and number of channels. Convolution is over height only.