yolov7-SAConv.py

class ConvAWS2d(nn.Conv2d):
    def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size,
                 stride=1,
                 padding=0,
                 dilation=1,
                 groups=1,
                 bias=True):
        super().__init__(
            in_channels,
            out_channels,
            kernel_size,
            stride=stride,
            padding=padding,
            dilation=dilation,
            groups=groups,
            bias=bias)
        self.register_buffer('weight_gamma', torch.ones(self.out_channels, 1, 1, 1))
        self.register_buffer('weight_beta', torch.zeros(self.out_channels, 1, 1, 1))

    def _get_weight(self, weight):
        weight_mean = weight.mean(dim=1, keepdim=True).mean(dim=2,
                                  keepdim=True).mean(dim=3, keepdim=True)
        weight = weight - weight_mean
        std = torch.sqrt(weight.view(weight.size(0), -1).var(dim=1) + 1e-5).view(-1, 1, 1, 1)
        weight = weight / std
        weight = self.weight_gamma * weight + self.weight_beta
        return weight

    def forward(self, x):
        weight = self._get_weight(self.weight)
        return super()._conv_forward(x, weight, None)

    def _load_from_state_dict(self, state_dict, prefix, local_metadata, strict,
                              missing_keys, unexpected_keys, error_msgs):
        self.weight_gamma.data.fill_(-1)
        super()._load_from_state_dict(state_dict, prefix, local_metadata, strict,
                                      missing_keys, unexpected_keys, error_msgs)
        if self.weight_gamma.data.mean() > 0:
            return
        weight = self.weight.data
        weight_mean = weight.data.mean(dim=1, keepdim=True).mean(dim=2,
                                       keepdim=True).mean(dim=3, keepdim=True)
        self.weight_beta.data.copy_(weight_mean)
        std = torch.sqrt(weight.view(weight.size(0), -1).var(dim=1) + 1e-5).view(-1, 1, 1, 1)
        self.weight_gamma.data.copy_(std)
    
class SAConv2d(ConvAWS2d):
    def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size,
                 s=1,
                 p=None,
                 g=1,
                 d=1,
                 act=True,
                 bias=True):
        super().__init__(
            in_channels,
            out_channels,
            kernel_size,
            stride=s,
            padding=autopad(kernel_size, p),
            dilation=d,
            groups=g,
            bias=bias)
        self.switch = torch.nn.Conv2d(
            self.in_channels,
            1,
            kernel_size=1,
            stride=s,
            bias=True)
        self.switch.weight.data.fill_(0)
        self.switch.bias.data.fill_(1)
        self.weight_diff = torch.nn.Parameter(torch.Tensor(self.weight.size()))
        self.weight_diff.data.zero_()
        self.pre_context = torch.nn.Conv2d(
            self.in_channels,
            self.in_channels,
            kernel_size=1,
            bias=True)
        self.pre_context.weight.data.fill_(0)
        self.pre_context.bias.data.fill_(0)
        self.post_context = torch.nn.Conv2d(
            self.out_channels,
            self.out_channels,
            kernel_size=1,
            bias=True)
        self.post_context.weight.data.fill_(0)
        self.post_context.bias.data.fill_(0)
        
        self.bn = nn.BatchNorm2d(out_channels)
        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())

    def forward(self, x):
        # pre-context
        avg_x = torch.nn.functional.adaptive_avg_pool2d(x, output_size=1)
        avg_x = self.pre_context(avg_x)
        avg_x = avg_x.expand_as(x)
        x = x + avg_x
        # switch
        avg_x = torch.nn.functional.pad(x, pad=(2, 2, 2, 2), mode="reflect")
        avg_x = torch.nn.functional.avg_pool2d(avg_x, kernel_size=5, stride=1, padding=0)
        switch = self.switch(avg_x)
        # sac
        weight = self._get_weight(self.weight)
        out_s = super()._conv_forward(x, weight, None)
        ori_p = self.padding
        ori_d = self.dilation
        self.padding = tuple(3 * p for p in self.padding)
        self.dilation = tuple(3 * d for d in self.dilation)
        weight = weight + self.weight_diff
        out_l = super()._conv_forward(x, weight, None)
        out = switch * out_s + (1 - switch) * out_l
        self.padding = ori_p
        self.dilation = ori_d
        # post-context
        avg_x = torch.nn.functional.adaptive_avg_pool2d(out, output_size=1)
        avg_x = self.post_context(avg_x)
        avg_x = avg_x.expand_as(out)
        out = out + avg_x
        return self.act(self.bn(out))