oneflow.nn.GroupNorm

class oneflow.nn.GroupNorm(num_groups: int, num_channels: int, eps: float = 1e-05, affine: bool = True)

Applies Group Normalization over a mini-batch of inputs as described in the paper Group Normalization

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

The input channels are separated into num_groups groups, each containing num_channels / num_groups channels. The mean and standard-deviation are calculated separately over the each group. \(\gamma\) and \(\beta\) are learnable per-channel affine transform parameter vectors of size num_channels if affine is True. The standard-deviation is calculated via the biased estimator, equivalent to torch.var(input, unbiased=False).

This layer uses statistics computed from input data in both training and evaluation modes.

The interface is consistent with PyTorch. The documentation is referenced from: https://pytorch.org/docs/1.10/generated/torch.nn.GroupNorm.html.

Parameters
  • num_groups (int) – number of groups to separate the channels into

  • num_channels (int) – number of channels expected in input

  • eps – a value added to the denominator for numerical stability. Default: 1e-5

  • affine – a boolean value that when set to True, this module has learnable per-channel affine parameters initialized to ones (for weights) and zeros (for biases). Default: True.

Shape:
  • Input: \((N, C, *)\) where \(C=\text{num_channels}\)

  • Output: \((N, C, *)\) (same shape as input)

For example:

>>> import oneflow as flow
>>> import numpy as np
>>> input = flow.Tensor(np.random.randn(20, 6, 10, 10))
>>> # Separate 6 channels into 3 groups
>>> m = flow.nn.GroupNorm(3, 6)
>>> # Separate 6 channels into 6 groups (equivalent with InstanceNorm)
>>> m = flow.nn.GroupNorm(6, 6)
>>> # Put all 6 channels into a single group (equivalent with LayerNorm)
>>> m = flow.nn.GroupNorm(1, 6)
>>> # Activating the module
>>> output = m(input)