init

finetune/mmseg/models/utils/inverted_residual.py

@@ -0,0 +1,213 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from mmcv.cnn import ConvModule
+from torch import nn
+from torch.utils import checkpoint as cp
+
+from .se_layer import SELayer
+
+
+class InvertedResidual(nn.Module):
+    """InvertedResidual block for MobileNetV2.
+
+    Args:
+        in_channels (int): The input channels of the InvertedResidual block.
+        out_channels (int): The output channels of the InvertedResidual block.
+        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.
+        dilation (int): Dilation rate of depthwise conv. Default: 1
+        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='ReLU6').
+        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,
+                 stride,
+                 expand_ratio,
+                 dilation=1,
+                 conv_cfg=None,
+                 norm_cfg=dict(type='BN'),
+                 act_cfg=dict(type='ReLU6'),
+                 with_cp=False,
+                 **kwargs):
+        super().__init__()
+        self.stride = stride
+        assert stride in [1, 2], f'stride must in [1, 2]. ' \
+            f'But received {stride}.'
+        self.with_cp = with_cp
+        self.use_res_connect = self.stride == 1 and in_channels == out_channels
+        hidden_dim = int(round(in_channels * expand_ratio))
+
+        layers = []
+        if expand_ratio != 1:
+            layers.append(
+                ConvModule(
+                    in_channels=in_channels,
+                    out_channels=hidden_dim,
+                    kernel_size=1,
+                    conv_cfg=conv_cfg,
+                    norm_cfg=norm_cfg,
+                    act_cfg=act_cfg,
+                    **kwargs))
+        layers.extend([
+            ConvModule(
+                in_channels=hidden_dim,
+                out_channels=hidden_dim,
+                kernel_size=3,
+                stride=stride,
+                padding=dilation,
+                dilation=dilation,
+                groups=hidden_dim,
+                conv_cfg=conv_cfg,
+                norm_cfg=norm_cfg,
+                act_cfg=act_cfg,
+                **kwargs),
+            ConvModule(
+                in_channels=hidden_dim,
+                out_channels=out_channels,
+                kernel_size=1,
+                conv_cfg=conv_cfg,
+                norm_cfg=norm_cfg,
+                act_cfg=None,
+                **kwargs)
+        ])
+        self.conv = nn.Sequential(*layers)
+
+    def forward(self, x):
+
+        def _inner_forward(x):
+            if self.use_res_connect:
+                return x + self.conv(x)
+            else:
+                return self.conv(x)
+
+        if self.with_cp and x.requires_grad:
+            out = cp.checkpoint(_inner_forward, x)
+        else:
+            out = _inner_forward(x)
+
+        return out
+
+
+class InvertedResidualV3(nn.Module):
+    """Inverted Residual Block for MobileNetV3.
+
+    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 kernel 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. Default: None, which means no
+            se layer.
+        with_expand_conv (bool): Use expand conv or not. If set False,
+            mid_channels must be the same with in_channels. Default: True.
+        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,
+                 with_expand_conv=True,
+                 conv_cfg=None,
+                 norm_cfg=dict(type='BN'),
+                 act_cfg=dict(type='ReLU'),
+                 with_cp=False):
+        super().__init__()
+        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 = with_expand_conv
+
+        if self.with_se:
+            assert isinstance(se_cfg, dict)
+        if not self.with_expand_conv:
+            assert mid_channels == in_channels
+
+        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=dict(
+                type='Conv2dAdaptivePadding') if stride == 2 else 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