Change typo 'momemtum' to 'momentum' (#45045)
Summary:
As the title.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/45045
Reviewed By: mruberry
Differential Revision: D23808563
Pulled By: mrshenli
fbshipit-source-id: ca818377f4c23d67b037c146fef667ab8731961e
diff --git a/caffe2/python/data_parallel_model.py b/caffe2/python/data_parallel_model.py
index 365bc43..7f55274 100644
--- a/caffe2/python/data_parallel_model.py
+++ b/caffe2/python/data_parallel_model.py
@@ -941,7 +941,7 @@
uniq_blob_names = [stripBlobName(p) for p in blobs]
# Synchronize to the blob lookup map, as the provided
- # blobs might have non-parameters, such as momemtum blobs.
+ # blobs might have non-parameters, such as momentum blobs.
log.info("Creating checkpoint synchronization net")
devices = model.GetDevices()
for name in uniq_blob_names:
diff --git a/torch/nn/modules/batchnorm.py b/torch/nn/modules/batchnorm.py
index 7e19f12..0753118 100644
--- a/torch/nn/modules/batchnorm.py
+++ b/torch/nn/modules/batchnorm.py
@@ -387,7 +387,7 @@
This :attr:`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
- :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times \hat{x} + \text{momemtum} \times x_t`,
+ :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times \hat{x} + \text{momentum} \times x_t`,
where :math:`\hat{x}` is the estimated statistic and :math:`x_t` is the
new observed value.
diff --git a/torch/nn/modules/instancenorm.py b/torch/nn/modules/instancenorm.py
index 7624479..a0f9c9a 100644
--- a/torch/nn/modules/instancenorm.py
+++ b/torch/nn/modules/instancenorm.py
@@ -85,7 +85,7 @@
This :attr:`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
- :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times \hat{x} + \text{momemtum} \times x_t`,
+ :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times \hat{x} + \text{momentum} \times x_t`,
where :math:`\hat{x}` is the estimated statistic and :math:`x_t` is the
new observed value.
@@ -166,7 +166,7 @@
This :attr:`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
- :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times \hat{x} + \text{momemtum} \times x_t`,
+ :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times \hat{x} + \text{momentum} \times x_t`,
where :math:`\hat{x}` is the estimated statistic and :math:`x_t` is the
new observed value.
@@ -240,7 +240,7 @@
This :attr:`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
- :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times \hat{x} + \text{momemtum} \times x_t`,
+ :math:`\hat{x}_\text{new} = (1 - \text{momentum}) \times \hat{x} + \text{momentum} \times x_t`,
where :math:`\hat{x}` is the estimated statistic and :math:`x_t` is the
new observed value.
