YoloV5/YoloV7改进---注意力机制:引入GENet，效果优于SENet

###################### GENet  GatherExcite   ####     start   by  AI&CV  ###############################
import math, torch
from torch import nn as nn
import torch.nn.functional as F

from timm.models.layers.create_act import create_act_layer, get_act_layer
from timm.models.layers.create_conv2d import create_conv2d
from timm.models.layers.helpers import make_divisible
from timm.models.layers.mlp import ConvMlp


class GatherExcite(nn.Module):
    def __init__(
            self, channels, feat_size=None, extra_params=False, extent=0, use_mlp=True,
            rd_ratio=1./16, rd_channels=None,  rd_divisor=1, add_maxpool=False,
            act_layer=nn.ReLU, norm_layer=nn.BatchNorm2d, gate_layer='sigmoid'):
        super(GatherExcite, self).__init__()
        self.add_maxpool = add_maxpool
        act_layer = get_act_layer(act_layer)
        self.extent = extent
        if extra_params:
            self.gather = nn.Sequential()
            if extent == 0:
                assert feat_size is not None, 'spatial feature size must be specified for global extent w/ params'
                self.gather.add_module(
                    'conv1', create_conv2d(channels, channels, kernel_size=feat_size, stride=1, depthwise=True))
                if norm_layer:
                    self.gather.add_module(f'norm1', nn.BatchNorm2d(channels))
            else:
                assert extent % 2 == 0
                num_conv = int(math.log2(extent))
                for i in range(num_conv):
                    self.gather.add_module(
                        f'conv{i + 1}',
                        create_conv2d(channels, channels, kernel_size=3, stride=2, depthwise=True))
                    if norm_layer:
                        self.gather.add_module(f'norm{i + 1}', nn.BatchNorm2d(channels))
                    if i != num_conv - 1:
                        self.gather.add_module(f'act{i + 1}', act_layer(inplace=True))
        else:
            self.gather = None
            if self.extent == 0:
                self.gk = 0
                self.gs = 0
            else:
                assert extent % 2 == 0
                self.gk = self.extent * 2 - 1
                self.gs = self.extent

        if not rd_channels:
            rd_channels = make_divisible(channels * rd_ratio, rd_divisor, round_limit=0.)
        self.mlp = ConvMlp(channels, rd_channels, act_layer=act_layer) if use_mlp else nn.Identity()
        self.gate = create_act_layer(gate_layer)

    def forward(self, x):
        size = x.shape[-2:]
        if self.gather is not None:
            x_ge = self.gather(x)
        else:
            if self.extent == 0:
                # global extent
                x_ge = x.mean(dim=(2, 3), keepdims=True)
                if self.add_maxpool:
                    # experimental codepath, may remove or change
                    x_ge = 0.5 * x_ge + 0.5 * x.amax((2, 3), keepdim=True)
            else:
                x_ge = F.avg_pool2d(
                    x, kernel_size=self.gk, stride=self.gs, padding=self.gk // 2, count_include_pad=False)
                if self.add_maxpool:
                    # experimental codepath, may remove or change
                    x_ge = 0.5 * x_ge + 0.5 * F.max_pool2d(x, kernel_size=self.gk, stride=self.gs, padding=self.gk // 2)
        x_ge = self.mlp(x_ge)
        if x_ge.shape[-1] != 1 or x_ge.shape[-2] != 1:
            x_ge = F.interpolate(x_ge, size=size)
        return x * self.gate(x_ge)
###################### GENet  GatherExcite   ####     end   by  AI&CV  ###############################

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license

# Parameters
nc: 1  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # 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, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [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)
   [-1, 1, GlobalContext, [1024]],  # 24

   [[17, 20, 24], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]