Package smile.deep.layer


package smile.deep.layer
Neural network layers.
  • Class
    Description
    An adaptive average pooling that reduces a tensor by combining cells.
    An average pooling layer that reduces a tensor by combining cells, and assigning the average value of the input cells to the output cell.
    A batch normalization layer that re-centers and normalizes the output of one layer before feeding it to another.
    A batch normalization layer that re-centers and normalizes the output of one layer before feeding it to another.
    A convolutional layer.
    A dropout layer that randomly zeroes some of the elements of the input tensor with probability p during training.
    An embedding layer that is a simple lookup table that stores embeddings of a fixed dictionary and size.
    Group normalization.
    A layer in the neural network.
    A block is combinations of one or more layers.
    A fully connected linear layer.
    A max pooling layer that reduces a tensor by combining cells, and assigning the maximum value of the input cells to the output cell.
    Root Mean Square Layer Normalization.
    A block of sequential layers.