mirrors
/
mmpretrain
mirror of https://github.com/open-mmlab/mmpretrain.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[Fix] Fix optional issues in docstring (#138) 

* fix optional issue in docstring

* revised according to comments

* add optional
pull/139/head
LXXXXR 2021-01-14 11:09:08 +08:00 committed by GitHub
parent 6916f33d56
commit 63f38988eb
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
17 changed files with 82 additions and 84 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
mmcls/core/evaluation/eval_hooks.py
View File

@ -50,7 +50,7 @@ class DistEvalHook(EvalHook):
Args:
dataloader (DataLoader): A PyTorch dataloader.
interval (int): Evaluation interval (by epochs). Default: 1.
tmpdir (str | None): Temporary directory to save the results of all
tmpdir (str, optional): Temporary directory to save the results of all
processes. Default: None.
gpu_collect (bool): Whether to use gpu or cpu to collect results.
Default: False.

2
mmcls/datasets/pipelines/transforms.py
View File

@ -306,7 +306,7 @@ class RandomFlip(object):
Args:
flip_prob (float): probability of the image being flipped. Default: 0.5
direction (str, optional): The flipping direction. Options are
direction (str): The flipping direction. Options are
'horizontal' and 'vertical'. Default: 'horizontal'.
"""

4
mmcls/models/backbones/mobilenet_v2.py
View File

@ -20,7 +20,7 @@ class InvertedResidual(nn.Module):
stride (int): Stride of the middle (first) 3x3 convolution.
expand_ratio (int): adjusts number of channels of the hidden layer
in InvertedResidual by this amount.
conv_cfg (dict): Config dict for convolution layer.
conv_cfg (dict, optional): Config dict for convolution layer.
Default: None, which means using conv2d.
norm_cfg (dict): Config dict for normalization layer.
Default: dict(type='BN').
@ -108,7 +108,7 @@ class MobileNetV2(BaseBackbone):
Default: (7, ).
frozen_stages (int): Stages to be frozen (all param fixed).
Default: -1, which means not freezing any parameters.
conv_cfg (dict): Config dict for convolution layer.
conv_cfg (dict, optional): Config dict for convolution layer.
Default: None, which means using conv2d.
norm_cfg (dict): Config dict for normalization layer.
Default: dict(type='BN').

2
mmcls/models/backbones/mobilenet_v3.py
View File

@ -17,7 +17,7 @@ class MobileNetv3(BaseBackbone):
Args:
arch (str): Architechture of mobilnetv3, from {small, big}.
Default: small.
conv_cfg (dict): Config dict for convolution layer.
conv_cfg (dict, optional): Config dict for convolution layer.
Default: None, which means using conv2d.
norm_cfg (dict): Config dict for normalization layer.
Default: dict(type='BN').

2
mmcls/models/backbones/regnet.py
View File

@ -215,7 +215,7 @@ class RegNet(ResNet):
width_slope ([float]): Slope of the quantized linear function
width_parameter ([int]): Parameter used to quantize the width.
depth ([int]): Depth of the backbone.
divisor (int, optional): The divisor of channels. Defaults to 8.
divisor (int): The divisor of channels. Defaults to 8.
Returns:
list, int: return a list of widths of each stage and the number of

15
mmcls/models/backbones/resnest.py
View File

@ -47,9 +47,10 @@ class SplitAttentionConv2d(nn.Module):
radix (int): Radix of SpltAtConv2d. Default: 2
reduction_factor (int): Reduction factor of SplitAttentionConv2d.
Default: 4.
conv_cfg (dict): Config dict for convolution layer. Default: None,
which means using conv2d.
norm_cfg (dict): Config dict for normalization layer. Default: None.
conv_cfg (dict, optional): Config dict for convolution layer.
Default: None, which means using conv2d.
norm_cfg (dict, optional): Config dict for normalization layer.
Default: None.
"""
def __init__(self,
@ -145,13 +146,13 @@ class Bottleneck(_Bottleneck):
Bottleneck. Default: True.
stride (int): stride of the block. Default: 1
dilation (int): dilation of convolution. Default: 1
downsample (nn.Module): downsample operation on identity branch.
Default: None
downsample (nn.Module, optional): downsample operation on identity
branch. Default: None
style (str): `pytorch` or `caffe`. If set to "pytorch", the stride-two
layer is the 3x3 conv layer, otherwise the stride-two layer is
the first 1x1 conv layer.
conv_cfg (dict): dictionary to construct and config conv layer.
Default: None
conv_cfg (dict, optional): dictionary to construct and config conv
layer. Default: None
norm_cfg (dict): dictionary to construct and config norm layer.
Default: dict(type='BN')
with_cp (bool): Use checkpoint or not. Using checkpoint will save some

20
mmcls/models/backbones/resnet.py
View File

@ -19,14 +19,14 @@ class BasicBlock(nn.Module):
reserved argument in BasicBlock and should always be 1. Default: 1.
stride (int): stride of the block. Default: 1
dilation (int): dilation of convolution. Default: 1
downsample (nn.Module): downsample operation on identity branch.
Default: None.
downsample (nn.Module, optional): downsample operation on identity
branch. Default: None.
style (str): `pytorch` or `caffe`. It is unused and reserved for
unified API with Bottleneck.
with_cp (bool): Use checkpoint or not. Using checkpoint will save some
memory while slowing down the training speed.
conv_cfg (dict): dictionary to construct and config conv layer.
Default: None
conv_cfg (dict, optional): dictionary to construct and config conv
layer. Default: None
norm_cfg (dict): dictionary to construct and config norm layer.
Default: dict(type='BN')
"""
@ -130,15 +130,15 @@ class Bottleneck(nn.Module):
``mid_channels`` is the input/output channels of conv2. Default: 4.
stride (int): stride of the block. Default: 1
dilation (int): dilation of convolution. Default: 1
downsample (nn.Module): downsample operation on identity branch.
Default: None.
downsample (nn.Module, optional): downsample operation on identity
branch. Default: None.
style (str): ``"pytorch"`` or ``"caffe"``. If set to "pytorch", the
stride-two layer is the 3x3 conv layer, otherwise the stride-two
layer is the first 1x1 conv layer. Default: "pytorch".
with_cp (bool): Use checkpoint or not. Using checkpoint will save some
memory while slowing down the training speed.
conv_cfg (dict): dictionary to construct and config conv layer.
Default: None
conv_cfg (dict, optional): dictionary to construct and config conv
layer. Default: None
norm_cfg (dict): dictionary to construct and config norm layer.
Default: dict(type='BN')
"""
@ -309,8 +309,8 @@ class ResLayer(nn.Sequential):
stride (int): stride of the first block. Default: 1.
avg_down (bool): Use AvgPool instead of stride conv when
downsampling in the bottleneck. Default: False
conv_cfg (dict): dictionary to construct and config conv layer.
Default: None
conv_cfg (dict, optional): dictionary to construct and config conv
layer. Default: None
norm_cfg (dict): dictionary to construct and config norm layer.
Default: dict(type='BN')
"""

8
mmcls/models/backbones/resnext.py
View File

@ -17,13 +17,13 @@ class Bottleneck(_Bottleneck):
``groups=32, width_per_group=8``.
stride (int): stride of the block. Default: 1
dilation (int): dilation of convolution. Default: 1
downsample (nn.Module): downsample operation on identity branch.
Default: None
downsample (nn.Module, optional): downsample operation on identity
branch. Default: None
style (str): `pytorch` or `caffe`. If set to "pytorch", the stride-two
layer is the 3x3 conv layer, otherwise the stride-two layer is
the first 1x1 conv layer.
conv_cfg (dict): dictionary to construct and config conv layer.
Default: None
conv_cfg (dict, optional): dictionary to construct and config conv
layer. Default: None
norm_cfg (dict): dictionary to construct and config norm layer.
Default: dict(type='BN')
with_cp (bool): Use checkpoint or not. Using checkpoint will save some

8
mmcls/models/backbones/seresnext.py
View File

@ -19,14 +19,14 @@ class SEBottleneck(_SEBottleneck):
``groups=32, width_per_group=8``.
stride (int): stride of the block. Default: 1
dilation (int): dilation of convolution. Default: 1
downsample (nn.Module): downsample operation on identity branch.
Default: None
downsample (nn.Module, optional): downsample operation on identity
branch. Default: None
se_ratio (int): Squeeze ratio in SELayer. Default: 16
style (str): `pytorch` or `caffe`. If set to "pytorch", the stride-two
layer is the 3x3 conv layer, otherwise the stride-two layer is
the first 1x1 conv layer.
conv_cfg (dict): dictionary to construct and config conv layer.
Default: None
conv_cfg (dict, optional): dictionary to construct and config conv
layer. Default: None
norm_cfg (dict): dictionary to construct and config norm layer.
Default: dict(type='BN')
with_cp (bool): Use checkpoint or not. Using checkpoint will save some

22
mmcls/models/backbones/shufflenet_v1.py
View File

@ -22,20 +22,20 @@ class ShuffleUnit(nn.Module):
Args:
in_channels (int): The input channels of the ShuffleUnit.
out_channels (int): The output channels of the ShuffleUnit.
groups (int, optional): The number of groups to be used in grouped 1x1
groups (int): The number of groups to be used in grouped 1x1
convolutions in each ShuffleUnit. Default: 3
first_block (bool, optional): Whether it is the first ShuffleUnit of a
first_block (bool): Whether it is the first ShuffleUnit of a
sequential ShuffleUnits. Default: False, which means not using the
grouped 1x1 convolution.
combine (str, optional): The ways to combine the input and output
combine (str): The ways to combine the input and output
branches. Default: 'add'.
conv_cfg (dict): Config dict for convolution layer. Default: None,
which means using conv2d.
conv_cfg (dict, optional): Config dict for convolution layer.
Default: None, which means using conv2d.
norm_cfg (dict): Config dict for normalization layer.
Default: dict(type='BN').
act_cfg (dict): Config dict for activation layer.
Default: dict(type='ReLU').
with_cp (bool, optional): Use checkpoint or not. Using checkpoint
with_cp (bool): Use checkpoint or not. Using checkpoint
will save some memory while slowing down the training speed.
Default: False.
@ -154,16 +154,16 @@ class ShuffleNetV1(BaseBackbone):
"""ShuffleNetV1 backbone.
Args:
groups (int, optional): The number of groups to be used in grouped 1x1
groups (int): The number of groups to be used in grouped 1x1
convolutions in each ShuffleUnit. Default: 3.
widen_factor (float, optional): Width multiplier - adjusts the number
widen_factor (float): Width multiplier - adjusts the number
of channels in each layer by this amount. Default: 1.0.
out_indices (Sequence[int]): Output from which stages.
Default: (2, )
frozen_stages (int): Stages to be frozen (all param fixed).
Default: -1, which means not freezing any parameters.
conv_cfg (dict): Config dict for convolution layer. Default: None,
which means using conv2d.
conv_cfg (dict, optional): Config dict for convolution layer.
Default: None, which means using conv2d.
norm_cfg (dict): Config dict for normalization layer.
Default: dict(type='BN').
act_cfg (dict): Config dict for activation layer.
@ -276,7 +276,7 @@ class ShuffleNetV1(BaseBackbone):
Args:
out_channels (int): out_channels of the block.
num_blocks (int): Number of blocks.
first_block (bool, optional): Whether is the first ShuffleUnit of a
first_block (bool): Whether is the first ShuffleUnit of a
sequential ShuffleUnits. Default: False, which means not using
the grouped 1x1 convolution.
"""

4
mmcls/models/backbones/shufflenet_v2.py
View File

@ -19,7 +19,7 @@ class InvertedResidual(nn.Module):
in_channels (int): The input channels of the block.
out_channels (int): The output channels of the block.
stride (int): Stride of the 3x3 convolution layer. Default: 1
conv_cfg (dict): Config dict for convolution layer.
conv_cfg (dict, optional): Config dict for convolution layer.
Default: None, which means using conv2d.
norm_cfg (dict): Config dict for normalization layer.
Default: dict(type='BN').
@ -141,7 +141,7 @@ class ShuffleNetV2(BaseBackbone):
Default: (0, 1, 2, 3).
frozen_stages (int): Stages to be frozen (all param fixed).
Default: -1, which means not freezing any parameters.
conv_cfg (dict): Config dict for convolution layer.
conv_cfg (dict, optional): Config dict for convolution layer.
Default: None, which means using conv2d.
norm_cfg (dict): Config dict for normalization layer.
Default: dict(type='BN').

16
mmcls/models/backbones/vgg.py
View File

@ -44,14 +44,14 @@ class VGG(BaseBackbone):
num_classes (int): number of classes for classification.
num_stages (int): VGG stages, normally 5.
dilations (Sequence[int]): Dilation of each stage.
out_indices (Sequence[int]): Output from which stages. If only one
stage is specified, a single tensor (feature map) is returned,
otherwise multiple stages are specified, a tuple of tensors will
be returned. When it is None, the default behavior depends on
whether num_classes is specified. If num_classes <= 0, the default
value is (4, ), outputing the last feature map before classifier.
If num_classes > 0, the default value is (5, ), outputing the
classification score. Default: None.
out_indices (Sequence[int], optional): Output from which stages.
If only one stage is specified, a single tensor (feature map) is
returned, otherwise multiple stages are specified, a tuple of
tensors will be returned. When it is None, the default behavior
depends on whether num_classes is specified. If num_classes <= 0,
the default value is (4, ), outputing the last feature map before
classifier. If num_classes > 0, the default value is (5, ),
outputing the classification score. Default: None.
frozen_stages (int): Stages to be frozen (all param fixed). -1 means
not freezing any parameters.
norm_eval (bool): Whether to set norm layers to eval mode, namely,

4
mmcls/models/losses/accuracy.py
View File

@ -36,7 +36,7 @@ def accuracy(pred, target, topk=1):
Args:
pred (torch.Tensor | np.array): The model prediction.
target (torch.Tensor | np.array): The target of each prediction
topk (int | tuple[int], optional): If the predictions in ``topk``
topk (int | tuple[int]): If the predictions in ``topk``
matches the target, the predictions will be regarded as
correct ones. Defaults to 1.
@ -71,7 +71,7 @@ class Accuracy(nn.Module):
"""Module to calculate the accuracy
Args:
topk (tuple, optional): The criterion used to calculate the
topk (tuple): The criterion used to calculate the
accuracy. Defaults to (1,).
"""
super().__init__()

17
mmcls/models/losses/asymmetric_loss.py
View File

@ -24,12 +24,11 @@ def asymmetric_loss(pred,
shape (N, *).
weight (torch.Tensor, optional): Sample-wise loss weight with shape
(N, ). Dafaults to None.
gamma_pos (float, optional): positive focusing parameter.
Defaults to 0.0.
gamma_neg (float, optional): Negative focusing parameter. We usually
set gamma_neg > gamma_pos. Defaults to 4.0.
gamma_pos (float): positive focusing parameter. Defaults to 0.0.
gamma_neg (float): Negative focusing parameter. We usually set
gamma_neg > gamma_pos. Defaults to 4.0.
clip (float, optional): Probability margin. Defaults to 0.05.
reduction (str, optional): The method used to reduce the loss.
reduction (str): The method used to reduce the loss.
Options are "none", "mean" and "sum". If reduction is 'none' , loss
is same shape as pred and label. Defaults to 'mean'.
avg_factor (int, optional): Average factor that is used to average
@ -67,14 +66,14 @@ class AsymmetricLoss(nn.Module):
"""asymmetric loss
Args:
gamma_pos (float, optional): positive focusing parameter.
gamma_pos (float): positive focusing parameter.
Defaults to 0.0.
gamma_neg (float, optional): Negative focusing parameter. We
gamma_neg (float): Negative focusing parameter. We
usually set gamma_neg > gamma_pos. Defaults to 4.0.
clip (float, optional): Probability margin. Defaults to 0.05.
reduction (str, optional): The method used to reduce the loss into
reduction (str): The method used to reduce the loss into
a scalar.
loss_weight (float, optional): Weight of loss. Defaults to 1.0.
loss_weight (float): Weight of loss. Defaults to 1.0.
"""
def __init__(self,

15
mmcls/models/losses/cross_entropy_loss.py
View File

@ -13,10 +13,10 @@ def cross_entropy(pred, label, weight=None, reduction='mean', avg_factor=None):
of classes.
label (torch.Tensor): The learning label of the prediction.
weight (torch.Tensor, optional): Sample-wise loss weight.
reduction (str, optional): The method used to reduce the loss.
reduction (str): The method used to reduce the loss.
avg_factor (int, optional): Average factor that is used to average
the loss. Defaults to None.
class_weight (list[float], optional): The weight for each class.
Returns:
torch.Tensor: The calculated loss
"""
@ -44,7 +44,7 @@ def binary_cross_entropy(pred,
label (torch.Tensor): The learning label with shape (N, *).
weight (torch.Tensor, optional): Element-wise weight of loss with shape
(N, ). Defaults to None.
reduction (str, optional): The method used to reduce the loss.
reduction (str): The method used to reduce the loss.
Options are "none", "mean" and "sum". If reduction is 'none' , loss
is same shape as pred and label. Defaults to 'mean'.
avg_factor (int, optional): Average factor that is used to average
@ -73,12 +73,11 @@ class CrossEntropyLoss(nn.Module):
"""Cross entropy loss
Args:
use_sigmoid (bool, optional): Whether the prediction uses sigmoid
use_sigmoid (bool): Whether the prediction uses sigmoid
of softmax. Defaults to False.
reduction (str, optional): The method used to reduce the loss.
Options are "none", "mean" and "sum". Defaults to 'mean'.
loss_weight (float, optional): Weight of the loss.
Defaults to 1.0.
reduction (str): The method used to reduce the loss.
Options are "none", "mean" and "sum". Defaults to 'mean'.
loss_weight (float): Weight of the loss. Defaults to 1.0.
"""
def __init__(self, use_sigmoid=False, reduction='mean', loss_weight=1.0):

23
mmcls/models/losses/focal_loss.py
View File

@ -20,13 +20,12 @@ def sigmoid_focal_loss(pred,
shape (N, *).
weight (torch.Tensor, optional): Sample-wise loss weight with shape
(N, ). Dafaults to None.
gamma (float, optional): The gamma for calculating the modulating
factor. Defaults to 2.0.
alpha (float, optional): A balanced form for Focal Loss.
Defaults to 0.25.
reduction (str, optional): The method used to reduce the loss.
Options are "none", "mean" and "sum". If reduction is 'none' , loss
is same shape as pred and label. Defaults to 'mean'.
gamma (float): The gamma for calculating the modulating factor.
Defaults to 2.0.
alpha (float): A balanced form for Focal Loss. Defaults to 0.25.
reduction (str): The method used to reduce the loss.
Options are "none", "mean" and "sum". If reduction is 'none' ,
loss is same shape as pred and label. Defaults to 'mean'.
avg_factor (int, optional): Average factor that is used to average
the loss. Defaults to None.
@ -56,13 +55,13 @@ class FocalLoss(nn.Module):
"""Focal loss
Args:
gamma (float, optional): Focusing parameter in focal loss.
gamma (float): Focusing parameter in focal loss.
Defaults to 2.0.
alpha (float, optional): The parameter in balanced form of focal
alpha (float): The parameter in balanced form of focal
loss. Defaults to 0.25.
reduction (str, optional): The method used to reduce the loss into
reduction (str): The method used to reduce the loss into
a scalar. Options are "none" and "mean". Defaults to 'mean'.
loss_weight (float, optional): Weight of loss. Defaults to 1.0.
loss_weight (float): Weight of loss. Defaults to 1.0.
"""
def __init__(self,
@ -95,7 +94,7 @@ class FocalLoss(nn.Module):
the loss. Defaults to None.
reduction_override (str, optional): The method used to reduce the
loss into a scalar. Options are "none", "mean" and "sum".
Defaults to 'mean'.
Defaults to None.
Returns:
torch.Tensor: Loss.

2
mmcls/models/utils/make_divisible.py
View File

@ -9,7 +9,7 @@ def make_divisible(value, divisor, min_value=None, min_ratio=0.9):
divisor (int): The divisor to fully divide the channel number.
min_value (int, optional): The minimum value of the output channel.
Default: None, means that the minimum value equal to the divisor.
min_ratio (float, optional): The minimum ratio of the rounded channel
min_ratio (float): The minimum ratio of the rounded channel
number to the original channel number. Default: 0.9.
Returns:
int: The modified output channel number