Class InputLayer

  • All Implemented Interfaces:
    Layer, java.io.Serializable

    public class InputLayer
    extends AbstractLayer
    Input layer in neural network, which accepts external input, and sends it to next layer in a network. It is always the first layer in the network. Input can be 1D, 2D or 3D vectors/tensors of float values.
    Author:
    Zoran Sevarac
    See Also:
    Serialized Form
    • Constructor Detail

      • InputLayer

        public InputLayer​(int width,
                          int height,
                          int depth)
        Creates input layer with specified width, height, and depth (number of channels).
        Parameters:
        width - layer width
        height - layer height
        depth - layer depth (number of input channels)
      • InputLayer

        public InputLayer​(int width,
                          int height)
        Creates input layer with specified width and height, and depth=1 (single depth/channel).
        Parameters:
        width - layer width
        height - layer height
      • InputLayer

        public InputLayer​(int width)
        Creates input layer with specified width, and with height and depth equals to one.
        Parameters:
        width - layer width