brainpy.nn.nodes.ANN.BatchNorm#

class brainpy.nn.nodes.ANN.BatchNorm(axis, epsilon=1e-05, use_bias=True, use_scale=True, beta_init=ZeroInit, gamma_init=OneInit(value=1.0), **kwargs)[source]#

Batch Normalization node. This layer aims to reduce the internal covariant shift of data. It normalizes a batch of data by fixing the mean and variance of inputs on each feature (channel). Most commonly, the first axis of the data is the batch, and the last is the channel. However, users can specify the axes to be normalized.

adapted from jax.example_libraries.stax.BatchNorm https://jax.readthedocs.io/en/latest/_modules/jax/example_libraries/stax.html#BatchNorm

Parameters

axis (int, tuple, list) – axes where the data will be normalized. The feature (channel) axis should be excluded.
epsilon (float) – a value added to the denominator for numerical stability. Default: 1e-5
use_bias (bool) – whether to translate data in refactoring. Default: True
use_scale (bool) – whether to scale data in refactoring. Default: True
beta_init (brainpy.init.Initializer) – an initializer generating the original translation matrix
gamma_init (brainpy.init.Initializer) – an initializer generating the original scaling matrix

__init__(axis, epsilon=1e-05, use_bias=True, use_scale=True, beta_init=ZeroInit, gamma_init=OneInit(value=1.0), **kwargs)[source]#

Methods

`__init__`(axis[, epsilon, use_bias, ...])
`copy`([name, shallow])	Returns a copy of the Node.
`feedback`(ff_output, **shared_kwargs)	The feedback computation function of a node.
`forward`(ff, **shared_kwargs)	The feedforward computation function of a node.
`init_fb_conn`()	Initialize the feedback connections.
`init_fb_output`([num_batch])	Set the initial node feedback state.
`init_ff_conn`()	Initialize the feedforward connections.
`init_state`([num_batch])	Set the initial node state.
`initialize`([num_batch])	Initialize the node.
`load_states`(filename[, verbose])	Load the model states.
`nodes`([method, level, include_self])	Collect all children nodes.
`offline_fit`(targets, ffs[, fbs])	Offline training interface.
`online_fit`(target, ff[, fb])	Online training fitting interface.
`online_init`()	Online training initialization interface.
`register_implicit_nodes`(nodes)
`register_implicit_vars`(variables)
`save_states`(filename[, variables])	Save the model states.
`set_fb_output`(state)	Safely set the feedback state of the node.
`set_feedback_shapes`(fb_shapes)
`set_feedforward_shapes`(feedforward_shapes)
`set_output_shape`(shape)
`set_state`(state)	Safely set the state of the node.
`train_vars`([method, level, include_self])	The shortcut for retrieving all trainable variables.
`unique_name`([name, type_])	Get the unique name for this object.
`vars`([method, level, include_self])	Collect all variables in this node and the children nodes.

Attributes

`data_pass`	Offline fitting method.
`fb_output`	rtype `Optional`[`TypeVar`(`Tensor`, `JaxArray`, `ndarray`)]
`feedback_shapes`	Output data size.
`feedforward_shapes`	Input data size.
`is_feedback_input_supported`
`is_feedback_supported`
`is_initialized`	rtype `bool`
`name`
`output_shape`	Output data size.
`state`	Node current internal state.
`trainable`	Returns if the Node can be trained.