Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Fix] Fix the docstring for initializers #1071

Merged
merged 3 commits into from
Jun 1, 2021
Merged

[Fix] Fix the docstring for initializers #1071

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8554e47
[WIP] Updata initialization documents
MeowZheng May 28, 2021
a91ccf5
Merge branch 'master' into init_doc
MeowZheng Jun 1, 2021
0b8c168
[Fix] Fix the docstring for initializers
MeowZheng Jun 1, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 6 additions & 12 deletions mmcv/cnn/utils/weight_init.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,8 +131,7 @@ class ConstantInit(BaseInit):

Args:
val (int | float): the value to fill the weights in the module with
bias (int | float): the value to fill the bias or
define initialization type for bias. Defaults to 0.
bias (int | float): the value to fill the bias. Defaults to 0.
bias_prob (float, optional): the probability for bias initialization.
Defaults to None.
layer (str | list[str], optional): the layer will be initialized.
Expand Down Expand Up @@ -166,8 +165,7 @@ class XavierInit(BaseInit):

Args:
gain (int | float): an optional scaling factor. Defaults to 1.
bias (int | float): the value to fill the bias or define
initialization type for bias. Defaults to 0.
bias (int | float): the value to fill the bias. Defaults to 0.
bias_prob (float, optional): the probability for bias initialization.
Defaults to None.
distribution (str): distribution either be ``'normal'``
Expand Down Expand Up @@ -204,8 +202,7 @@ class NormalInit(BaseInit):
mean (int | float):the mean of the normal distribution. Defaults to 0.
std (int | float): the standard deviation of the normal distribution.
Defaults to 1.
bias (int | float): the value to fill the bias or define
initialization type for bias. Defaults to 0.
bias (int | float): the value to fill the bias. Defaults to 0.
bias_prob (float, optional): the probability for bias initialization.
Defaults to None.
layer (str | list[str], optional): the layer will be initialized.
Expand Down Expand Up @@ -244,8 +241,7 @@ class TruncNormalInit(BaseInit):
Defaults to 1.
a (float): The minimum cutoff value.
b ( float): The maximum cutoff value.
bias (float): the value to fill the bias or define
initialization type for bias. Defaults to 0.
bias (float): the value to fill the bias. Defaults to 0.
bias_prob (float, optional): the probability for bias initialization.
Defaults to None.
layer (str | list[str], optional): the layer will be initialized.
Expand Down Expand Up @@ -291,8 +287,7 @@ class UniformInit(BaseInit):
Defaults to 0.
b (int | float): the upper bound of the uniform distribution.
Defaults to 1.
bias (int | float): the value to fill the bias or define
initialization type for bias. Defaults to 0.
bias (int | float): the value to fill the bias. Defaults to 0.
bias_prob (float, optional): the probability for bias initialization.
Defaults to None.
layer (str | list[str], optional): the layer will be initialized.
Expand Down Expand Up @@ -336,8 +331,7 @@ class KaimingInit(BaseInit):
nonlinearity (str): the non-linear function (`nn.functional` name),
recommended to use only with ``'relu'`` or ``'leaky_relu'`` .
Defaults to 'relu'.
bias (int | float): the value to fill the bias or define
initialization type for bias. Defaults to 0.
bias (int | float): the value to fill the bias. Defaults to 0.
bias_prob (float, optional): the probability for bias initialization.
Defaults to None.
distribution (str): distribution either be ``'normal'`` or
Expand Down