class ChannelAttention(nn.Module):
    # Channel-attention module https://github.com/open-mmlab/mmdetection/tree/v3.0.0rc1/configs/rtmdet
    def __init__(self, channels: int) -> None:
        super().__init__()
        self.pool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Conv2d(channels, channels, 1, 1, 0, bias=True)
        self.act = nn.Sigmoid()
    def forward(self, x: torch.Tensor) -> torch.Tensor:
        return x * self.act(self.fc(self.pool(x)))
class SpatialAttention(nn.Module):
    # Spatial-attention module
    def __init__(self, kernel_size=7):
        super().__init__()
        assert kernel_size in (3, 7), 'kernel size must be 3 or 7'
        padding = 3 if kernel_size == 7 else 1
        self.cv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False)
        self.act = nn.Sigmoid()
    def forward(self, x):
        return x * self.act(self.cv1(torch.cat([torch.mean(x, 1, keepdim=True), torch.max(x, 1, keepdim=True)[0]], 1)))
class CBAM(nn.Module):
    # Convolutional Block Attention Module
    def __init__(self, c1, kernel_size=7):  # ch_in, kernels
        super().__init__()
        self.channel_attention = ChannelAttention(c1)
        self.spatial_attention = SpatialAttention(kernel_size)
    def forward(self, x):
        return self.spatial_attention(self.channel_attention(x))

def channel_shuffle(x, groups=2):  ##shuffle channel
    # RESHAPE----->transpose------->Flatten
    B, C, H, W = x.size()
    out = x.view(B, groups, C // groups, H, W).permute(0, 2, 1, 3, 4).contiguous()
    out = out.view(B, C, H, W)
    return out
class GAM_Attention(nn.Module):
    # https://paperswithcode.com/paper/global-attention-mechanism-retain-information
    def __init__(self, c1, c2, group=True, rate=4):
        super(GAM_Attention, self).__init__()
        self.channel_attention = nn.Sequential(
            nn.Linear(c1, int(c1 / rate)),
            nn.ReLU(inplace=True),
            nn.Linear(int(c1 / rate), c1)
        )
        self.spatial_attention = nn.Sequential(
            nn.Conv2d(c1, c1 // rate, kernel_size=7, padding=3, groups=rate) if group else nn.Conv2d(c1, int(c1 / rate),
                                                                                                     kernel_size=7,
                                                                                                     padding=3),
            nn.BatchNorm2d(int(c1 / rate)),
            nn.ReLU(inplace=True),
            nn.Conv2d(c1 // rate, c2, kernel_size=7, padding=3, groups=rate) if group else nn.Conv2d(int(c1 / rate), c2,
                                                                                                     kernel_size=7,
                                                                                                     padding=3),
            nn.BatchNorm2d(c2)
        )
    def forward(self, x):
        b, c, h, w = x.shape
        x_permute = x.permute(0, 2, 3, 1).view(b, -1, c)
        x_att_permute = self.channel_attention(x_permute).view(b, h, w, c)
        x_channel_att = x_att_permute.permute(0, 3, 1, 2)
        # x_channel_att=channel_shuffle(x_channel_att,4) #last shuffle
        x = x * x_channel_att
        x_spatial_att = self.spatial_attention(x).sigmoid()
        x_spatial_att = channel_shuffle(x_spatial_att, 4)  # last shuffle
        out = x * x_spatial_att
        # out=channel_shuffle(out,4) #last shuffle
        return out

class ResBlock_CBAM(nn.Module):
    def __init__(self, in_places, places, stride=1, downsampling=False, expansion=4):
        super(ResBlock_CBAM, self).__init__()
        self.expansion = expansion
        self.downsampling = downsampling
        self.bottleneck = nn.Sequential(
            nn.Conv2d(in_channels=in_places, out_channels=places, kernel_size=1, stride=1, bias=False),
            nn.BatchNorm2d(places),
            nn.LeakyReLU(0.1, inplace=True),
            nn.Conv2d(in_channels=places, out_channels=places, kernel_size=3, stride=stride, padding=1, bias=False),
            nn.BatchNorm2d(places),
            nn.LeakyReLU(0.1, inplace=True),
            nn.Conv2d(in_channels=places, out_channels=places * self.expansion, kernel_size=1, stride=1,
                        bias=False),
            nn.BatchNorm2d(places * self.expansion),
        )
        self.cbam = CBAM(c1=places * self.expansion, c2=places * self.expansion, )
        if self.downsampling:
            self.downsample = nn.Sequential(
                nn.Conv2d(in_channels=in_places, out_channels=places * self.expansion, kernel_size=1, stride=stride,
                            bias=False),
                nn.BatchNorm2d(places * self.expansion)
            )
        self.relu = nn.ReLU(inplace=True)
    def forward(self, x):
        residual = x
        out = self.bottleneck(x)
        out = self.cbam(out)
        if self.downsampling:
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out

from ultralytics.nn.modules import (C1, C2, C3, C3TR, SPP, SPPF, Bottleneck, BottleneckCSP, C2f, C3Ghost, C3x, Classify,
                                    Concat, Conv, ConvTranspose, Detect, DWConv, DWConvTranspose2d, Ensemble, Focus,
                                    GhostBottleneck, GhostConv, Segment,CBAM, GAM_Attention , ResBlock_CBAM)

 if m in (Classify, Conv, ConvTranspose, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, Focus,
                 BottleneckCSP, C1, C2, C2f, C3, C3TR, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x , CBAM , GAM_Attention ,ResBlock_CBAM):