gsnn.gsnn.models.GroupEMANorm

class gsnn.gsnn.models.GroupEMANorm(*args: Any, **kwargs: Any)[source]

Bases: Module

Applies normalization within each channel group using exponential moving averages.

This normalization maintains running statistics but doesn’t use current batch statistics for normalization, making it very stable for small batch sizes.

Parameters:

  • channel_groups (list or tensor) – Specifies which group each channel belongs to.

  • eps (float) – Small value to avoid division by zero. Default: 1e-5

  • momentum (float) – Momentum for updating running statistics. Default: 0.1

  • affine (bool) – If True, applies learnable scale and bias. Default: True

  • track_running_stats (bool) – If True, maintains running statistics. Default: True

__init__(channel_groups, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)[source]

Methods

__init__(channel_groups[, eps, momentum, ...])

forward(x)

Normalize using per-group running EMA stats (updated while training).
forward(x)[source]

Normalize using per-group running EMA stats (updated while training).