inox.nn.normalization#
Normalization layers
Classes#
Descriptions#
- class inox.nn.normalization.BatchNorm(channels, epsilon=1e-05, momentum=0.9)#
Creates a batch-normalization layer.
\[y = \frac{x - \mathbb{E}[x]}{\sqrt{\mathbb{V}[x] + \epsilon}}\]The mean and variance are calculated over the batch and spatial axes. During training, the layer keeps running estimates of the mean and variance, which are then used for normalization during evaluation. The update rule for a running average statistic \(\hat{s}\) is
\[\hat{s} \gets \alpha \hat{s} + (1 - \alpha) s\]where \(s\) is the statistic calculated for the current batch.
References
Accelerating Deep Network Training by Reducing Internal Covariate Shift (Ioffe et al., 2015)- Parameters:
- class inox.nn.normalization.LayerNorm(axis=-1, epsilon=1e-05)#
Creates a layer-normalization layer.
\[y = \frac{x - \mathbb{E}[x]}{\sqrt{\mathbb{V}[x] + \epsilon}}\]References
Layer Normalization (Ba et al., 2016)- Parameters:
- class inox.nn.normalization.GroupNorm(groups, epsilon=1e-05)#
Creates a group-normalization layer.
References
Group Normalization (Wu et al., 2018)- Parameters: