keras

BatchNormalization

keras.layers.normalization.BatchNormalization(input_shape, epsilon=1e-6, weights=None)

Normalize the activations of the previous layer at each batch.

• Input shape: Same as input_shape. This layer cannot be used as first layer in a model.

• Output shape: Same as input.

• Arguments:

  • input_shape: tuple.
  • epsilon: small float > 0. Fuzz parameter.
  • weights: Initialization weights. List of 2 numpy arrays, with shapes: [(input_shape,), (input_shape,)]

• References:

  • Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift