learning/annotated_deep_learning_paper_implementations
1
0
Fork 0
mirror of https://github.com/labmlai/annotated_deep_learning_paper_implementations.git synced 2025-08-15 10:11:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

keepdims -> keepdim

Browse Source
This commit is contained in:
Varuna Jayasiri
2021-04-20 17:07:49 +05:30
parent e47e0a5c82
commit cbdd26ffec
3 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
labml_nn/normalization/group_norm/__init__.py
View File

@ -60,10 +60,10 @@ class GroupNorm(Module):
# Calculate the mean across first and last dimension; # Calculate the mean across first and last dimension;
# i.e. the means for each feature $\mathbb{E}[x^{(k)}]$ # i.e. the means for each feature $\mathbb{E}[x^{(k)}]$
mean = x.mean(dim=[2], keepdims=True) mean = x.mean(dim=[2], keepdim=True)
# Calculate the squared mean across first and last dimension; # Calculate the squared mean across first and last dimension;
# i.e. the means for each feature $\mathbb{E}[(x^{(k)})^2]$ # i.e. the means for each feature $\mathbb{E}[(x^{(k)})^2]$
mean_x2 = (x ** 2).mean(dim=[2], keepdims=True) mean_x2 = (x ** 2).mean(dim=[2], keepdim=True)
# Variance for each feature $Var[x^{(k)}] = \mathbb{E}[(x^{(k)})^2] - \mathbb{E}[x^{(k)}]^2$ # Variance for each feature $Var[x^{(k)}] = \mathbb{E}[(x^{(k)})^2] - \mathbb{E}[x^{(k)}]^2$
var = mean_x2 - mean ** 2 var = mean_x2 - mean ** 2

4
labml_nn/normalization/instance_norm/__init__.py
View File

@ -57,10 +57,10 @@ class InstanceNorm(Module):
# Calculate the mean across first and last dimension; # Calculate the mean across first and last dimension;
# i.e. the means for each feature $\mathbb{E}[x^{(k)}]$ # i.e. the means for each feature $\mathbb{E}[x^{(k)}]$
mean = x.mean(dim=[2], keepdims=True) mean = x.mean(dim=[2], keepdim=True)
# Calculate the squared mean across first and last dimension; # Calculate the squared mean across first and last dimension;
# i.e. the means for each feature $\mathbb{E}[(x^{(k)})^2]$ # i.e. the means for each feature $\mathbb{E}[(x^{(k)})^2]$
mean_x2 = (x ** 2).mean(dim=[2], keepdims=True) mean_x2 = (x ** 2).mean(dim=[2], keepdim=True)
# Variance for each feature $Var[x^{(k)}] = \mathbb{E}[(x^{(k)})^2] - \mathbb{E}[x^{(k)}]^2$ # Variance for each feature $Var[x^{(k)}] = \mathbb{E}[(x^{(k)})^2] - \mathbb{E}[x^{(k)}]^2$
var = mean_x2 - mean ** 2 var = mean_x2 - mean ** 2

4
labml_nn/normalization/layer_norm/__init__.py
View File

@ -106,10 +106,10 @@ class LayerNorm(Module):
# Calculate the mean of all elements; # Calculate the mean of all elements;
# i.e. the means for each element $\mathbb{E}[X]$ # i.e. the means for each element $\mathbb{E}[X]$
mean = x.mean(dim=dims, keepdims=True) mean = x.mean(dim=dims, keepdim=True)
# Calculate the squared mean of all elements; # Calculate the squared mean of all elements;
# i.e. the means for each element $\mathbb{E}[X^2]$ # i.e. the means for each element $\mathbb{E}[X^2]$
mean_x2 = (x ** 2).mean(dim=dims, keepdims=True) mean_x2 = (x ** 2).mean(dim=dims, keepdim=True)
# Variance of all element $Var[X] = \mathbb{E}[X^2] - \mathbb{E}[X]^2$ # Variance of all element $Var[X] = \mathbb{E}[X^2] - \mathbb{E}[X]^2$
var = mean_x2 - mean ** 2 var = mean_x2 - mean ** 2