# brainpy.layers.BatchNorm2d#

class brainpy.layers.BatchNorm2d(num_features, axis=(0, 1, 2), epsilon=1e-05, momentum=0.99, affine=True, bias_initializer=ZeroInit, scale_initializer=OneInit(value=1.0), axis_name=None, axis_index_groups=None, mode=None, name=None)[source]#

2-D batch normalization [1].

The data should be of (b, h, w, c), where b is the batch dimension, h is the height dimension, w is the width dimension, and c is the channel dimension.

$y=\frac{x-\mathrm{E}[x]}{\sqrt{\operatorname{Var}[x]+\epsilon}} * \gamma+\beta$

Note

This momentum argument is different from one used in optimizer classes and the conventional notion of momentum. Mathematically, the update rule for running statistics here is $$\hat{x}_\text{new} = \text{momentum} \times \hat{x} + (1-\text{momentum}) \times x_t$$, where $$\hat{x}$$ is the estimated statistic and $$x_t$$ is the new observed value.

Parameters:
• num_features (int) – C from an expected input of size (B, H, W, C).

• 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

• momentum (float) – The value used for the running_mean and running_var computation. Default: 0.99

• affine (bool) – A boolean value that when set to True, this module has learnable affine parameters. Default: True

• bias_initializer (Initializer, ArrayType, Callable) – an initializer generating the original translation matrix

• scale_initializer (Initializer, ArrayType, Callable) – an initializer generating the original scaling matrix

• axis_name (optional, str, sequence of str) – If not None, it should be a string (or sequence of strings) representing the axis name(s) over which this module is being run within a jax map (e.g. jax.pmap or jax.vmap). Supplying this argument means that batch statistics are calculated across all replicas on the named axes.

• axis_index_groups (optional, sequence) – Specifies how devices are grouped. Valid only within jax.pmap collectives.

References

__init__(num_features, axis=(0, 1, 2), epsilon=1e-05, momentum=0.99, affine=True, bias_initializer=ZeroInit, scale_initializer=OneInit(value=1.0), axis_name=None, axis_index_groups=None, mode=None, name=None)[source]#

Methods

 __init__(num_features[, axis, epsilon, ...]) clear_input() cpu() Move all variable into the CPU device. cuda() Move all variables into the GPU device. get_delay_data(identifier, delay_step, *indices) Get delay data according to the provided delay steps. load_state_dict(state_dict[, warn, compatible]) Copy parameters and buffers from state_dict into this module and its descendants. load_states(filename[, verbose]) Load the model states. nodes([method, level, include_self]) Collect all children nodes. register_delay(identifier, delay_step, ...) Register delay variable. register_implicit_nodes(*nodes[, node_cls]) register_implicit_vars(*variables[, var_cls]) reset(*args, **kwargs) Reset function which reset the whole variables in the model. reset_local_delays([nodes]) Reset local delay variables. reset_state(*args, **kwargs) Reset function which reset the states in the model. save_states(filename[, variables]) Save the model states. state_dict() Returns a dictionary containing a whole state of the module. to(device) Moves all variables into the given device. tpu() Move all variables into the TPU device. train_vars([method, level, include_self]) The shortcut for retrieving all trainable variables. tree_flatten() Flattens the object as a PyTree. tree_unflatten(aux, dynamic_values) Unflatten the data to construct an object of this class. unique_name([name, type_]) Get the unique name for this object. update(x) The function to specify the updating rule. update_local_delays([nodes]) Update local delay variables. vars([method, level, include_self, ...]) Collect all variables in this node and the children nodes.

Attributes

 global_delay_data Global delay data, which stores the delay variables and corresponding delay targets. mode Mode of the model, which is useful to control the multiple behaviors of the model. name Name of the model.