mirrors/mmclassification
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmclassification.git synced 2025-06-03 21:53:55 +08:00
Code Issues Projects Releases Wiki Activity

Update default value

Browse Source
This commit is contained in:
lixiaojie 2020-06-14 03:51:42 +08:00
parent 02e1c246b4
commit 461e07d65d
1 changed files with 9 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
mmcls/models/backbones/shufflenet_v2.py
View File

@ -65,13 +65,17 @@ class InvertedResidual(nn.Module):
inplanes (int): The input channels of the block. inplanes (int): The input channels of the block.
planes (int): The output channels of the block. planes (int): The output channels of the block.
stride (int): stride of the 3x3 convolution layer. Default: 1 stride (int): stride of the 3x3 convolution layer. Default: 1
conv_cfg (dict): Config dict for convolution layer. Default: None, conv_cfg (dict): Config dict for convolution layer.
which means using conv2d. Default: None, which means using conv2d.
norm_cfg (dict): Config dict for normalization layer. Default: None. norm_cfg (dict): Config dict for normalization layer.
Default: dict(type='BN').
act_cfg (dict): Config dict for activation layer. act_cfg (dict): Config dict for activation layer.
Default: dict(type='ReLU'). Default: dict(type='ReLU').
with_cp (bool, optional): Use checkpoint or not. Using checkpoint norm_eval (bool): Whether to set norm layers to eval mode, namely,
will save some memory while slowing down the training speed. freeze running stats (mean and var). Note: Effect on Batch Norm
and its variants only. Default: True.
with_cp (bool): Use checkpoint or not. Using checkpoint will save some
memory while slowing down the training speed. Default: False.
Returns: Returns:
Tensor: The output tensor. Tensor: The output tensor.