OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-06 12:20:52 +01:00
Code Issues Actions 38 Packages Projects Releases Wiki Activity

Changed 'standard-deviation' to 'variance' in GroupNorm documentation (#141982)

Browse Source 
Fixes #141315

Updated the GroupNorm documentation to replace 'standard-deviation' with 'variance' to accurately reflect the calculation
method.

@pytorchbot label "topic: not user facing"
Pull Request resolved: https://github.com/pytorch/pytorch/pull/141982
Approved by: https://github.com/mikaylagawarecki
This commit is contained in:
UV 2024-12-04 22:49:43 +00:00 committed by PyTorch MergeBot
parent 326f487809
commit 0318589e87
3 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
torch/nn/modules/batchnorm.py
View File

@ -280,9 +280,9 @@ class BatchNorm1d(_BatchNorm):
the mini-batches and :math:`\gamma` and :math:`\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 :math:`\gamma` are set to 1 and the elements of :math:`\beta` are set to 0.
At train time in the forward pass, the standard-deviation is calculated via the biased estimator,
At train time in the forward pass, the variance is calculated via the biased estimator,
equivalent to ``torch.var(input, unbiased=False)``. However, the value stored in the
moving average of the standard-deviation is calculated via the unbiased estimator, equivalent to
moving average of the variance is calculated via the unbiased estimator, equivalent to
``torch.var(input, unbiased=True)``.
Also by default, during training this layer keeps running estimates of its

2
torch/nn/modules/instancenorm.py
View File

@ -139,7 +139,7 @@ class InstanceNorm1d(_InstanceNorm):
The mean and standard-deviation are calculated per-dimension separately
for each object in a mini-batch. :math:`\gamma` and :math:`\beta` are learnable parameter vectors
of size `C` (where `C` is the number of features or channels of the input) if :attr:`affine` is ``True``.
The standard-deviation is calculated via the biased estimator, equivalent to
The variance is calculated via the biased estimator, equivalent to
`torch.var(input, unbiased=False)`.
By default, this layer uses instance statistics computed from input data in

4
torch/nn/modules/normalization.py
View File

@ -106,7 +106,7 @@ class LayerNorm(Module):
the last 2 dimensions of the input (i.e. ``input.mean((-2, -1))``).
:math:`\gamma` and :math:`\beta` are learnable affine transform parameters of
:attr:`normalized_shape` if :attr:`elementwise_affine` is ``True``.
The standard-deviation is calculated via the biased estimator, equivalent to
The variance is calculated via the biased estimator, equivalent to
`torch.var(input, unbiased=False)`.
.. note::
@ -240,7 +240,7 @@ class GroupNorm(Module):
separately over the each group. :math:`\gamma` and :math:`\beta` are learnable
per-channel affine transform parameter vectors of size :attr:`num_channels` if
:attr:`affine` is ``True``.
The standard-deviation is calculated via the biased estimator, equivalent to
The variance 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