Package ai.djl.nn.norm

Class LayerNorm

java.lang.Object
ai.djl.nn.AbstractBaseBlock
ai.djl.nn.AbstractBlock
ai.djl.nn.norm.LayerNorm
All Implemented Interfaces:
Block
public class LayerNorm extends AbstractBlock
Layer normalization works by normalizing the values of input data for each input sample to have mean of 0 and variance of 1. Since this may alter the representation of a layer, two parameters (\ (\gamma\) and \(\beta\)) are learned along the normalization process to respectively scale and shift the normalized output (activations) to have any mean and variance so the network can utilize non-linear transformations such as sigmoid function as described in the paper. During backpropagation, both \(\gamma\) and \(\beta\) parameters are included following the chain-rule in derivation.

Citing the abstract of the paper: "Training state-of-the-art, deep neural networks is computationally expensive. One way to reduce the training time is to normalize the activities of the neurons. A recently introduced technique called batch normalization uses the distribution of the summed input to a neuron over a mini-batch of training cases to compute a mean and variance which are then used to normalize the summed input to that neuron on each training case. This significantly reduces the training time in feed-forward neural networks. However, the effect of batch normalization is dependent on the mini-batch size and it is not obvious how to apply it to recurrent neural networks. In this paper, we transpose batch normalization into layer normalization by computing the mean and variance used for normalization from all of the summed inputs to the neurons in a layer on a single training case. Like batch normalization, we also give each neuron its own adaptive bias and gain which are applied after the normalization but before the non-linearity. Unlike batch normalization, layer normalization performs exactly the same computation at training and test times. It is also straightforward to apply to recurrent neural networks by computing the normalization statistics separately at each time step. Layer normalization is very effective at stabilizing the hidden state dynamics in recurrent networks. Empirically, we show that layer normalization can substantially reduce the training time compared with previously published techniques."

  • Field Details

    • epsilon

      protected float epsilon

    • normalizedShape

      protected Shape normalizedShape

    • center

      protected boolean center

    • scale

      protected boolean scale

    • axis

      protected int[] axis

    • gamma

      protected Parameter gamma

    • beta

      protected Parameter beta

  • Constructor Details

  • Method Details

    • layerNorm

      public static NDList layerNorm(NDArray input, Shape normalizedShape, NDArray gamma, NDArray beta, float eps)
      Applies Layer Normalization with average and variance for each input sample across the axis dimensions.
      Parameters:
      input - the input NDArray of shape (batchSize, inputChannel, *), * could be empty, width, (height, width), (depth, height, width)
      normalizedShape - dimensions to calculate average and variance from
      gamma - gamma weight NDArray
      beta - beta weight NDArray
      eps - a value added to the denominator for numerical stability
      Returns:
      the output NDArray of shape (batchSize, inputChannel, *), * could be empty, width, (height, width), (depth, height, width)

    • builder

      public static LayerNorm.Builder builder()
      Creates a builder to build a LayerNorm.
      Returns:
      a new builder

    • forwardInternal

      protected NDList forwardInternal(ParameterStore parameterStore, NDList inputs, boolean training, ai.djl.util.PairList<String,Object> params)
      A helper for Block.forward(ParameterStore, NDList, boolean, PairList) after initialization.
      Specified by:
      forwardInternal in class AbstractBaseBlock
      Parameters:
      parameterStore - the parameter store
      inputs - the input NDList
      training - true for a training forward pass
      params - optional parameters
      Returns:
      the output of the forward pass

    • getOutputShapes

      public Shape[] getOutputShapes(Shape[] inputShapes)
      Returns the expected output shapes of the block for the specified input shapes.
      Parameters:
      inputShapes - the shapes of the inputs
      Returns:
      the expected output shapes of the block

    • beforeInitialize

      protected void beforeInitialize(Shape... inputShapes)
      Performs any action necessary before initialization. For example, keep the input information or verify the layout.
      Overrides:
      beforeInitialize in class AbstractBaseBlock
      Parameters:
      inputShapes - the expected shapes of the input

    • prepare

      public void prepare(Shape[] inputShapes)
      Sets the shape of Parameters.
      Overrides:
      prepare in class AbstractBaseBlock
      Parameters:
      inputShapes - the shapes of inputs

    • saveMetadata

      protected void saveMetadata(DataOutputStream os) throws IOException
      Override this method to save additional data apart from parameter values.

      This default implementation saves the currently set input shapes.

      Overrides:
      saveMetadata in class AbstractBaseBlock
      Parameters:
      os - the non-null output stream the parameter values and metadata are written to
      Throws:
      IOException - saving failed

    • loadMetadata

      public void loadMetadata(byte loadVersion, DataInputStream is) throws IOException, MalformedModelException
      Overwrite this to load additional metadata with the parameter values.

      If you overwrite AbstractBaseBlock.saveMetadata(DataOutputStream) or need to provide backward compatibility to older binary formats, you probably need to overwrite this. This default implementation checks if the version number fits, if not it throws an MalformedModelException. After that it restores the input shapes.

      Overrides:
      loadMetadata in class AbstractBaseBlock
      Parameters:
      loadVersion - the version used for loading this metadata.
      is - the input stream we are loading from
      Throws:
      IOException - loading failed
      MalformedModelException - data can be loaded but has wrong format