| import mmcv | |
| import torch.nn as nn | |
| from mmcv.cnn import ConvModule | |
| from .make_divisible import make_divisible | |
| class SELayer(nn.Module): | |
| """Squeeze-and-Excitation Module. | |
| Args: | |
| channels (int): The input (and output) channels of the SE layer. | |
| ratio (int): Squeeze ratio in SELayer, the intermediate channel will be | |
| ``int(channels/ratio)``. Default: 16. | |
| conv_cfg (None or dict): Config dict for convolution layer. | |
| Default: None, which means using conv2d. | |
| act_cfg (dict or Sequence[dict]): Config dict for activation layer. | |
| If act_cfg is a dict, two activation layers will be configurated | |
| by this dict. If act_cfg is a sequence of dicts, the first | |
| activation layer will be configurated by the first dict and the | |
| second activation layer will be configurated by the second dict. | |
| Default: (dict(type='ReLU'), dict(type='HSigmoid', bias=3.0, | |
| divisor=6.0)). | |
| """ | |
| def __init__(self, | |
| channels, | |
| ratio=16, | |
| conv_cfg=None, | |
| act_cfg=(dict(type='ReLU'), | |
| dict(type='HSigmoid', bias=3.0, divisor=6.0))): | |
| super(SELayer, self).__init__() | |
| if isinstance(act_cfg, dict): | |
| act_cfg = (act_cfg, act_cfg) | |
| assert len(act_cfg) == 2 | |
| assert mmcv.is_tuple_of(act_cfg, dict) | |
| self.global_avgpool = nn.AdaptiveAvgPool2d(1) | |
| self.conv1 = ConvModule( | |
| in_channels=channels, | |
| out_channels=make_divisible(channels // ratio, 8), | |
| kernel_size=1, | |
| stride=1, | |
| conv_cfg=conv_cfg, | |
| act_cfg=act_cfg[0]) | |
| self.conv2 = ConvModule( | |
| in_channels=make_divisible(channels // ratio, 8), | |
| out_channels=channels, | |
| kernel_size=1, | |
| stride=1, | |
| conv_cfg=conv_cfg, | |
| act_cfg=act_cfg[1]) | |
| def forward(self, x): | |
| out = self.global_avgpool(x) | |
| out = self.conv1(out) | |
| out = self.conv2(out) | |
| return x * out | |