torch.nn.modules.batchnorm
Members list
Grouped members
nn_conv TODO use dtype
Applies Batch Normalization over a 2D or 3D input as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift .
Applies Batch Normalization over a 2D or 3D input as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift .
$$y = \frac{x  \mathrm{E}[x]}{\sqrt{\mathrm{Var}[x] + \epsilon}} * \gamma + \beta$$
The mean and standarddeviation are calculated perdimension over the minibatches and $\gamma$ and $\beta$ are learnable parameter vectors of size [C] (where [C] is the number of features or channels of the input). By default, the elements of $\gamma$ are set to 1 and the elements of $\beta$ are set to 0. The standarddeviation is calculated via the biased estimator, equivalent to [torch.var(input, unbiased=False)].
Also by default, during training this layer keeps running estimates of its computed mean and variance, which are then used for normalization during evaluation. The running estimates are kept with a default momentum
of 0.1.
If trackRunningStats
is set to false
, this layer then does not keep running estimates, and batch statistics are instead used during evaluation time as well.
Example:
import torch.nn
// With Learnable Parameters
var m = nn.BatchNorm1d(numFeatures = 100)
// Without Learnable Parameters
m = nn.BatchNorm1d(100, affine = false)
val input = torch.randn(Seq(20, 100))
val output = m(input)
Value parameters
 affine:

a boolean value that when set to
true
, this module has learnable affine parameters. Default:True
 eps:

a value added to the denominator for numerical stability. Default: 1e5
 momentum

the value used for the runningVean and runningVar computation. Can be set to
None
for cumulative moving average (i.e. simple average). Default: 0.1  numFeatures

number of features or channels $C$ of the input
 trackRunningStats:

a boolean value that when set to
true
, this module tracks the running mean and variance, and when set tofalse
, this module does not track such statistics, and initializes statistics buffersrunningMean
andrunningVar
asNone
. When these buffers areNone
, this module always uses batch statistics. in both training and eval modes. Default:true
Shape: Input: $(N, C)$ or $(N, C, L)$, where $N$ is the batch size, $C$ is the number of features or channels, and $L$ is the sequence length
 Output: $(N, C)$ or $(N, C, L)$ (same shape as input)
Attributes
 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 $\hat{x}_\text{new} = (1  \text{momentum}) \times \hat{x} + \text{momentum} \times x_t$, where $\hat{x}$ is the estimated statistic and $x_t$ is the new observed value. Because the Batch Normalization is done over the [C] dimension, computing statistics on [(N, L)] slices, it's common terminology to call this Temporal Batch Normalization. Args:  Source
 BatchNorm1d.scala
 Supertypes
Applies Batch Normalization over a 4D input as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift .
Applies Batch Normalization over a 4D input as described in the paper Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift .
$$y = \frac{x  \mathrm{E}[x]}{\sqrt{\mathrm{Var}[x] + \epsilon}} * \gamma + \beta$$
The mean and standarddeviation are calculated perdimension over the minibatches and $\gamma$ and $\beta$ are learnable parameter vectors of size [C] (where [C] is the number of features or channels of the input). By default, the elements of $\gamma$ are set to 1 and the elements of $\beta$ are set to 0. The standarddeviation is calculated via the biased estimator, equivalent to [torch.var(input, unbiased=False)].
Also by default, during training this layer keeps running estimates of its computed mean and variance, which are then used for normalization during evaluation. The running estimates are kept with a default momentum
of 0.1.
If trackRunningStats
is set to false
, this layer then does not keep running estimates, and batch statistics are instead used during evaluation time as well.
Example:
import torch.nn
// With Learnable Parameters
var m = nn.BatchNorm2d(numFeatures = 100)
// Without Learnable Parameters
m = nn.BatchNorm2d(100, affine = false)
val input = torch.randn(Seq(20, 100, 35, 45))
val output = m(input)
Value parameters
 affine:

a boolean value that when set to
true
, this module has learnable affine parameters. Default:True
 eps:

a value added to the denominator for numerical stability. Default: 1e5
 momentum

the value used for the runningVean and runningVar computation. Can be set to
None
for cumulative moving average (i.e. simple average). Default: 0.1  numFeatures

number of features or channels $C$ of the input
 trackRunningStats:

a boolean value that when set to
true
, this module tracks the running mean and variance, and when set tofalse
, this module does not track such statistics, and initializes statistics buffersrunningMean
andrunningVar
asNone
. When these buffers areNone
, this module always uses batch statistics. in both training and eval modes. Default:true
Shape: Input: $(N, C, H, W)$
 Output: $(N, C, H, W)$ (same shape as input)
Attributes
 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 $\hat{x}_\text{new} = (1  \text{momentum}) \times \hat{x} + \text{momentum} \times x_t$, where $\hat{x}$ is the estimated statistic and $x_t$ is the new observed value. Because the Batch Normalization is done over the C dimension, computing statistics on (N, H, W) slices, itâ€™s common terminology to call this Spatial Batch Normalization.  Source
 BatchNorm2d.scala
 Supertypes