mirror of
https://github.com/open-mmlab/mmclassification.git
synced 2025-06-03 21:53:55 +08:00
65410b05ad
* Refactor Mobilenetv3 structure and add ConvClsHead. * Change model's name from 'MobileNetv3' to 'MobileNetV3' * Modify configs for MobileNetV3 on CIFAR10. And add MobileNetV3 configs for imagenet * Fix activate setting bugs in MobileNetV3. And remove bias in SELayer. * Modify unittest * Remove useless config and file. * Fix mobilenetv3-large arch setting * Add dropout option in ConvClsHead * Fix MobilenetV3 structure according to torchvision version. 1. Remove with_expand_conv option in InvertedResidual, it should be decided by channels. 2. Revert activation function, should before SE layer. * Format code. * Rename MobilenetV3 arch "big" to "large". * Add mobilenetv3_small torchvision training recipe * Modify default `out_indices` of MobilenetV3, now it will change according to `arch` if not specified. * Add MobilenetV3 large config. * Add mobilenetv3 README * Modify InvertedResidual unit test. * Refactor ConvClsHead to StackedLinearClsHead, and add unit tests. * Add unit test for `simple_test` of `StackedLinearClsHead`. * Fix typo Co-authored-by: Yidi Shao <ydshao@smail.nju.edu.cn>
114 lines
3.6 KiB
Python
114 lines
3.6 KiB
Python
import torch.utils.checkpoint as cp
|
|
from mmcv.cnn import ConvModule
|
|
from mmcv.runner import BaseModule
|
|
|
|
from .se_layer import SELayer
|
|
|
|
|
|
# class InvertedResidual(nn.Module):
|
|
class InvertedResidual(BaseModule):
|
|
"""Inverted Residual Block.
|
|
|
|
Args:
|
|
in_channels (int): The input channels of this Module.
|
|
out_channels (int): The output channels of this Module.
|
|
mid_channels (int): The input channels of the depthwise convolution.
|
|
kernel_size (int): The kernal size of the depthwise convolution.
|
|
Default: 3.
|
|
stride (int): The stride of the depthwise convolution. Default: 1.
|
|
se_cfg (dict): Config dict for se layer. Defaul: None, which means no
|
|
se layer.
|
|
conv_cfg (dict): 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): Use checkpoint or not. Using checkpoint will save some
|
|
memory while slowing down the training speed. Default: False.
|
|
|
|
Returns:
|
|
Tensor: The output tensor.
|
|
"""
|
|
|
|
def __init__(self,
|
|
in_channels,
|
|
out_channels,
|
|
mid_channels,
|
|
kernel_size=3,
|
|
stride=1,
|
|
se_cfg=None,
|
|
conv_cfg=None,
|
|
norm_cfg=dict(type='BN'),
|
|
act_cfg=dict(type='ReLU'),
|
|
with_cp=False,
|
|
init_cfg=None):
|
|
super(InvertedResidual, self).__init__(init_cfg)
|
|
self.with_res_shortcut = (stride == 1 and in_channels == out_channels)
|
|
assert stride in [1, 2]
|
|
self.with_cp = with_cp
|
|
self.with_se = se_cfg is not None
|
|
self.with_expand_conv = (mid_channels != in_channels)
|
|
|
|
if self.with_se:
|
|
assert isinstance(se_cfg, dict)
|
|
|
|
if self.with_expand_conv:
|
|
self.expand_conv = ConvModule(
|
|
in_channels=in_channels,
|
|
out_channels=mid_channels,
|
|
kernel_size=1,
|
|
stride=1,
|
|
padding=0,
|
|
conv_cfg=conv_cfg,
|
|
norm_cfg=norm_cfg,
|
|
act_cfg=act_cfg)
|
|
self.depthwise_conv = ConvModule(
|
|
in_channels=mid_channels,
|
|
out_channels=mid_channels,
|
|
kernel_size=kernel_size,
|
|
stride=stride,
|
|
padding=kernel_size // 2,
|
|
groups=mid_channels,
|
|
conv_cfg=conv_cfg,
|
|
norm_cfg=norm_cfg,
|
|
act_cfg=act_cfg)
|
|
if self.with_se:
|
|
self.se = SELayer(**se_cfg)
|
|
self.linear_conv = ConvModule(
|
|
in_channels=mid_channels,
|
|
out_channels=out_channels,
|
|
kernel_size=1,
|
|
stride=1,
|
|
padding=0,
|
|
conv_cfg=conv_cfg,
|
|
norm_cfg=norm_cfg,
|
|
act_cfg=None)
|
|
|
|
def forward(self, x):
|
|
|
|
def _inner_forward(x):
|
|
out = x
|
|
|
|
if self.with_expand_conv:
|
|
out = self.expand_conv(out)
|
|
|
|
out = self.depthwise_conv(out)
|
|
|
|
if self.with_se:
|
|
out = self.se(out)
|
|
|
|
out = self.linear_conv(out)
|
|
|
|
if self.with_res_shortcut:
|
|
return x + out
|
|
else:
|
|
return out
|
|
|
|
if self.with_cp and x.requires_grad:
|
|
out = cp.checkpoint(_inner_forward, x)
|
|
else:
|
|
out = _inner_forward(x)
|
|
|
|
return out
|