convolutional

Type Members

1. abstract class Convolution extends Node

   

   Base class for convolutional layers.

2. class Convolution1D extends Convolution with Layer

   

   1D convolution for structured image-like inputs.

   1D convolution for structured image-like inputs. Input should have two dimensions: height and number of channels. Convolution is over height only.

3. class Convolution2D extends Convolution with Layer

   

   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.

4. class Convolution3D extends Convolution with Layer

   

   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.

5. class Cropping1D extends Node with Layer

   

   1D cropping layer

6. class Cropping2D extends Node with Layer

   

   2D cropping layer

7. class Cropping3D extends Node with Layer

   

   3D cropping layer

8. class Upsampling extends Node

   

   Base upsampling layer

9. class Upsampling1D extends Upsampling with Layer

   

   1D upsampling layer

10. class Upsampling2D extends Upsampling with Layer

    

    2D upsampling layer

11. class Upsampling3D extends Upsampling with Layer

    

    3D upsampling layer

12. class ZeroPadding1D extends Node with Layer

    

    1D zero padding layer

13. class ZeroPadding2D extends Node with Layer

    

    2D zero padding layer

14. class ZeroPadding3D extends Node with Layer

    

    3D zero padding layer