layers3.batch_norm

class layers3.batch_norm(decay=0.01, epsilon=1e-05, is_training=None, values=None)

Basic batch normalization layer

__init__(decay=0.01, epsilon=1e-05, is_training=None, values=None)

Parameters:

• decay (float) – Decay rate.
• epsilon (float) – Epsilon value to avoid 0 division.
• is_training (bool) – Define whether this layer is in training mode
• values (list[np.array]) – If the param ‘values’ is set, the layer will be initialized with the list of numpy array.

build(input_shape)

Creates the variables of the layer (optional, for subclass implementers).

This is a method that implementers of subclasses of Layer or Model can override if they need a state-creation step in-between layer instantiation and layer call.

This is typically used to create the weights of Layer subclasses.

Parameters:input_shape – Instance of TensorShape, or list of instances of TensorShape if the layer expects a list of inputs (one instance per input).

call(x)

Parameters:x – Input tensor or numpy array. The object will be automatically converted to tensor if the input is np.array. Note that other arrays in args or kwargs will not be auto-converted.

update(variable, value)