import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.autograd

class Attention(nn.Module):
    def __init__(self, in_planes, out_planes, kernel_size, groups=1, reduction=0.0625, kernel_num=4, min_channel=16):
        super(Attention, self).__init__()
        attention_channel = max(int(in_planes * reduction), min_channel)
        self.kernel_size = kernel_size
        self.kernel_num = kernel_num
        self.temperature = 1.0

        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Conv2d(in_planes, attention_channel, 1, bias=False)
        self.bn = nn.BatchNorm2d(attention_channel)
        self.relu = nn.ReLU(inplace=True)

        self.channel_fc = nn.Conv2d(attention_channel, in_planes, 1, bias=True)
        self.func_channel = self.get_channel_attention

        if in_planes == groups and in_planes == out_planes:  # depth-wise convolution
            self.func_filter = self.skip
        else:
            self.filter_fc = nn.Conv2d(attention_channel, out_planes, 1, bias=True)
            self.func_filter = self.get_filter_attention

        if kernel_size == 1:  # point-wise convolution
            self.func_spatial = self.skip
        else:
            self.spatial_fc = nn.Conv2d(attention_channel, kernel_size * kernel_size, 1, bias=True)
            self.func_spatial = self.get_spatial_attention

        if kernel_num == 1:
            self.func_kernel = self.skip
        else:
            self.kernel_fc = nn.Conv2d(attention_channel, kernel_num, 1, bias=True)
            self.func_kernel = self.get_kernel_attention

        self._initialize_weights()

    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            if isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

    def update_temperature(self, temperature):
        self.temperature = temperature

    @staticmethod
    def skip(_):
        return 1.0

    def get_channel_attention(self, x):
        channel_attention = torch.sigmoid(self.channel_fc(x).view(x.size(0), -1, 1, 1) / self.temperature)
        return channel_attention

    def get_filter_attention(self, x):
        filter_attention = torch.sigmoid(self.filter_fc(x).view(x.size(0), -1, 1, 1) / self.temperature)
        return filter_attention

    def get_spatial_attention(self, x):
        spatial_attention = self.spatial_fc(x).view(x.size(0), 1, 1, 1, self.kernel_size, self.kernel_size)
        spatial_attention = torch.sigmoid(spatial_attention / self.temperature)
        return spatial_attention

    def get_kernel_attention(self, x):
        kernel_attention = self.kernel_fc(x).view(x.size(0), -1, 1, 1, 1, 1)
        kernel_attention = F.softmax(kernel_attention / self.temperature, dim=1)
        return kernel_attention

    def forward(self, x):
        x = self.avgpool(x)
        x = self.fc(x)
        # x = self.bn(x) # 在外面我提供了一个bn这里会报错
        x = self.relu(x)
        return self.func_channel(x), self.func_filter(x), self.func_spatial(x), self.func_kernel(x)


class ODConv2d(nn.Module):
    def __init__(self, in_planes, out_planes, kernel_size=3, stride=1, padding=1, dilation=1, groups=1,
                 reduction=0.0625, kernel_num=4):
        super(ODConv2d, self).__init__()
        in_planes = in_planes
        self.in_planes = in_planes
        self.out_planes = out_planes
        self.kernel_size = kernel_size
        self.stride = stride
        self.padding = padding
        self.dilation = dilation
        self.groups = groups
        self.kernel_num = kernel_num
        self.attention = Attention(in_planes, out_planes, kernel_size, groups=groups,
                                   reduction=reduction, kernel_num=kernel_num)
        self.weight = nn.Parameter(torch.randn(kernel_num, out_planes, in_planes//groups, kernel_size, kernel_size),
                                   requires_grad=True)
        self._initialize_weights()

        if self.kernel_size == 1 and self.kernel_num == 1:
            self._forward_impl = self._forward_impl_pw1x
        else:
            self._forward_impl = self._forward_impl_common

    def _initialize_weights(self):
        for i in range(self.kernel_num):
            nn.init.kaiming_normal_(self.weight[i], mode='fan_out', nonlinearity='relu')

    def update_temperature(self, temperature):
        self.attention.update_temperature(temperature)

    def _forward_impl_common(self, x):
        # Multiplying channel attention (or filter attention) to weights and feature maps are equivalent,
        # while we observe that when using the latter method the models will run faster with less gpu memory cost.
        channel_attention, filter_attention, spatial_attention, kernel_attention = self.attention(x)
        batch_size, in_planes, height, width = x.size()
        x = x * channel_attention
        x = x.reshape(1, -1, height, width)
        aggregate_weight = spatial_attention * kernel_attention * self.weight.unsqueeze(dim=0)
        aggregate_weight = torch.sum(aggregate_weight, dim=1).view(
            [-1, self.in_planes // self.groups, self.kernel_size, self.kernel_size])
        output = F.conv2d(x, weight=aggregate_weight, bias=None, stride=self.stride, padding=self.padding,
                          dilation=self.dilation, groups=self.groups * batch_size)
        output = output.view(batch_size, self.out_planes, output.size(-2), output.size(-1))
        output = output * filter_attention
        return output

    def _forward_impl_pw1x(self, x):
        channel_attention, filter_attention, spatial_attention, kernel_attention = self.attention(x)
        x = x * channel_attention
        output = F.conv2d(x, weight=self.weight.squeeze(dim=0), bias=None, stride=self.stride, padding=self.padding,
                          dilation=self.dilation, groups=self.groups)
        output = output * filter_attention
        return output

    def forward(self, x):
        return self._forward_impl(x)



class Bottleneck(nn.Module):
    """Standard bottleneck."""

    def __init__(self, c1, c2, shortcut=True, g=1, k=(3, 3), e=0.5):
        """Initializes a bottleneck module with given input/output channels, shortcut option, group, kernels, and
        expansion.
        """
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, k[0], 1)
        self.cv2 = ODConv2d(c_, c2, k[1], 1)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        """'forward()' applies the YOLO FPN to input data."""
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))


class C3_ODConv(nn.Module):
    # CSP Bottleneck with 3 convolutions
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.cv3 = Conv(2 * c_, c2, 1)  # optional act=FReLU(c2)
        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))

    def forward(self, x):
        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))

# Ultralytics YOLOv5 🚀, AGPL-3.0 license
 
# Parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
anchors:
  - [10, 13, 16, 30, 33, 23] # P3/8
  - [30, 61, 62, 45, 59, 119] # P4/16
  - [116, 90, 156, 198, 373, 326] # P5/32

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3_ODConv, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3_ODConv, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3_ODConv, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3_ODConv, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]