阅读量:0
轻量化YOLOv7系列：结合G-GhostNet | 适配GPU，华为诺亚提出G-Ghost方案升级GhostNet
本文提供了改进 YOLOv7注意力系列包含不同的注意力机制以及多种加入方式，在本文中具有完整的代码和包含多种更有效加入YOLOv8中的yaml结构，读者可以获取到注意力加入的代码和使用经验，总有一种适合你和你的数据集。
🗝️YOLOv7实战宝典--星级指南：从入门到精通，您不可错过的技巧
-- 聚焦于YOLO的 最新版本， 对颈部网络改进、添加局部注意力、增加检测头部，实测涨点💡 深入浅出YOLOv7：我的专业笔记与技术总结
-- YOLOv7轻松上手， 适用技术小白，文章代码齐全，仅需 一键train，解决 YOLOv7的技术突破和创新潜能❤️ YOLOv8创新攻略：突破技术瓶颈，激发AI新潜能"
-- 指导独特且专业的分析， 也支持对YOLOv3、YOLOv4、YOLOv5、YOLOv6等网络的修改🎈 改进YOLOv7专栏内容《YOLOv7实战宝典》📖 ，改进点包括： 替换多种骨干网络/轻量化网络，添加40多种注意力， 包含自注意力/上下文注意力/自顶向下注意力机制/空间通道注意力/，设计不同的网络结构，助力涨点！！！
YOLOv7注意力系列包含不同的注意力机制
需要修改的代码
models/GGhostRegNet.py代码
- 新建这个文件，放入网络代码
import torch import torch.nn as nn import torch.nn.functional as F def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1): """3x3 convolution with padding""" return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=dilation, groups=groups, bias=False, dilation=dilation) def conv1x1(in_planes, out_planes, stride=1): """1x1 convolution""" return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False) class GHOSTBottleneck(nn.Module): expansion = 1 __constants__ = ['downsample'] def __init__(self, inplanes, planes, stride=1, downsample=None, group_width=1, dilation=1, norm_layer=None): super(GHOSTBottleneck, self).__init__() if norm_layer is None: norm_layer = nn.BatchNorm2d width = planes * self.expansion # Both self.conv2 and self.downsample layers downsample the input when stride != 1 self.conv1 = conv1x1(inplanes, width) self.bn1 = norm_layer(width) self.conv2 = conv3x3(width, width, stride, width // min(width, group_width), dilation) self.bn2 = norm_layer(width) self.conv3 = conv1x1(width, planes) self.bn3 = norm_layer(planes) self.relu = nn.SiLU(inplace=True) self.downsample = downsample self.stride = stride def forward(self, x): identity = x out = self.conv1(x) out = self.bn1(out) out = self.relu(out) out = self.conv2(out) out = self.bn2(out) out = self.relu(out) out = self.conv3(out) out = self.bn3(out) if self.downsample is not None: identity = self.downsample(x) out += identity out = self.relu(out) return out # class LambdaLayer(nn.Module): # def __init__(self, lambd): # super(LambdaLayer, self).__init__() # self.lambd = lambd # # def forward(self, x): # return self.lambd(x) class Stage(nn.Module): def __init__(self, block, inplanes, planes, group_width, blocks, stride=1, dilate=False, cheap_ratio=0.5): super(Stage, self).__init__() norm_layer = nn.BatchNorm2d downsample = None self.dilation = 1 previous_dilation = self.dilation self.inplanes = inplanes if dilate: self.dilation *= stride stride = 1 if stride != 1 or self.inplanes != planes: downsample = nn.Sequential( conv1x1(inplanes, planes, stride), norm_layer(planes), ) self.base = block(inplanes, planes, stride, downsample, group_width, previous_dilation, norm_layer) self.end = block(planes, planes, group_width=group_width, dilation=self.dilation, norm_layer=norm_layer) group_width = int(group_width * 0.75) raw_planes = int(planes * (1 - cheap_ratio) / group_width) * group_width cheap_planes = planes - raw_planes self.cheap_planes = cheap_planes self.raw_planes = raw_planes self.merge = nn.Sequential( nn.AdaptiveAvgPool2d(1), nn.Conv2d(planes + raw_planes * (blocks - 2), cheap_planes, kernel_size=1, stride=1, bias=False), nn.BatchNorm2d(cheap_planes), nn.SiLU(inplace=True), nn.Conv2d(cheap_planes, cheap_planes, kernel_size=1, bias=False), nn.BatchNorm2d(cheap_planes), ) self.cheap = nn.Sequential( nn.Conv2d(cheap_planes, cheap_planes, kernel_size=1, stride=1, bias=False), nn.BatchNorm2d(cheap_planes), ) self.cheap_relu = nn.SiLU(inplace=True) layers = [] # downsample = nn.Sequential( # LambdaLayer(lambda x: x[:, :raw_planes]) # ) layers = [] layers.append(block(raw_planes, raw_planes, 1, downsample, group_width, self.dilation, norm_layer)) inplanes = raw_planes for _ in range(2, blocks - 1): layers.append(block(inplanes, raw_planes, group_width=group_width, dilation=self.dilation, norm_layer=norm_layer)) self.layers = nn.Sequential(*layers) def forward(self, input): x0 = self.base(input) m_list = [x0] e = x0[:, :self.raw_planes] for l in self.layers: e = l(e) m_list.append(e) m = torch.cat(m_list, 1) m = self.merge(m) c = x0[:, self.raw_planes:] c = self.cheap_relu(self.cheap(c) + m) x = torch.cat((e, c), 1) x = self.end(x) return x class GGhostRegNet(nn.Module): def __init__(self, block, layers, widths, layer_number, num_classes=1000, zero_init_residual=True, group_width=8, replace_stride_with_dilation=None, norm_layer=None): super(GGhostRegNet, self).__init__() # --------------------------------- self.layer_number = layer_number # -------------------------------------- if norm_layer is None: norm_layer = nn.BatchNorm2d self._norm_layer = norm_layer self.inplanes = widths[0] self.dilation = 1 if replace_stride_with_dilation is None: # each element in the tuple indicates if we should replace # the 2x2 stride with a dilated convolution instead replace_stride_with_dilation = [False, False, False, False] if len(replace_stride_with_dilation) != 4: raise ValueError("replace_stride_with_dilation should be None " "or a 4-element tuple, got {}".format(replace_stride_with_dilation)) self.group_width = group_width # self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=3, stride=2, padding=1, # bias=False) # self.bn1 = norm_layer(self.inplanes) # self.relu = nn.ReLU(inplace=True) if self.layer_number in [0]: self.layer1 = self._make_layer(block, widths[0], layers[0], stride=1, dilate=replace_stride_with_dilation[0]) if self.layer_number in [1]: self.inplanes = widths[0] if layers[1] > 2: self.layer2 = Stage(block, self.inplanes, widths[1], group_width, layers[1], stride=1, dilate=replace_stride_with_dilation[1], cheap_ratio=0.5) else: self.layer2 = self._make_layer(block, widths[1], layers[1], stride=1, dilate=replace_stride_with_dilation[1]) if self.layer_number in [2]: self.inplanes = widths[1] self.layer3 = Stage(block, self.inplanes, widths[2], group_width, layers[2], stride=1, dilate=replace_stride_with_dilation[2], cheap_ratio=0.5) if self.layer_number in [3]: self.inplanes = widths[2] if layers[3] > 2: self.layer4 = Stage(block, self.inplanes, widths[3], group_width, layers[3], stride=1, dilate=replace_stride_with_dilation[3], cheap_ratio=0.5) else: self.layer4 = self._make_layer(block, widths[3], layers[3], stride=1, dilate=replace_stride_with_dilation[3]) # self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) # self.dropout = nn.Dropout(0.2) # self.fc = nn.Linear(widths[-1] * block.expansion, num_classes) for m in self.modules(): if isinstance(m, nn.Conv2d): nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)): nn.init.constant_(m.weight, 1) nn.init.constant_(m.bias, 0) def _make_layer(self, block, planes, blocks, stride=1, dilate=False): norm_layer = self._norm_layer downsample = None previous_dilation = self.dilation if dilate: self.dilation *= stride stride = 1 if stride != 1 or self.inplanes != planes: downsample = nn.Sequential( conv1x1(self.inplanes, planes, stride), norm_layer(planes), ) layers = [] layers.append(block(self.inplanes, planes, stride, downsample, self.group_width, previous_dilation, norm_layer)) self.inplanes = planes for _ in range(1, blocks): layers.append(block(self.inplanes, planes, group_width=self.group_width, dilation=self.dilation, norm_layer=norm_layer)) return nn.Sequential(*layers) def _forward_impl(self, x): if self.layer_number in [0]: x = self.layer1(x) if self.layer_number in [1]: x = self.layer2(x) if self.layer_number in [2]: x = self.layer3(x) if self.layer_number in [3]: x = self.layer4(x) return x def forward(self, x): return self._forward_impl(x) 
- yolo里引用
创建yaml文件
# parameters nc: 80 # number of classes depth_multiple: 1.0 # model depth multiple width_multiple: 1.0 # layer channel multiple # anchors anchors: - [12,16, 19,36, 40,28] # P3/8 - [36,75, 76,55, 72,146] # P4/16 - [142,110, 192,243, 459,401] # P5/32 # yolov7_MY backbone backbone: # [from, number, module, args] [[-1, 1, Conv, [32, 3, 1]], # 0 [-1, 1, Conv, [64, 3, 2]], # 1-P1/2 [-1, 1, Conv, [64, 3, 1]], [-1, 1, Conv, [128, 3, 2]], # 3-P2/4 [-1, 1, Conv, [48, 1, 1]], # [-2, 1, Conv, [64, 1, 1]], # [-1, 1, Conv, [64, 3, 1]], # [-1, 1, Conv, [64, 3, 1]], # [-1, 1, Conv, [64, 3, 1]], # [-1, 1, Conv, [64, 3, 1]], # [[-1, -3, -5, -6], 1, Concat, [1]], # [-1, 1, Conv, [256, 1, 1]], # 11 [-1, 1, GGhostRegNet, [48, 0]], # 5 [-1, 1, MP, []], [-1, 1, Conv, [48, 1, 1]], [-3, 1, Conv, [48, 1, 1]], [-1, 1, Conv, [48, 3, 2]], [[-1, -3], 1, Concat, [1]], # 16-P3/8 [-1, 1, Conv, [96, 1, 1]], # [-2, 1, Conv, [128, 1, 1]], # [-1, 1, Conv, [128, 3, 1]], # [-1, 1, Conv, [128, 3, 1]], # [-1, 1, Conv, [128, 3, 1]], # [-1, 1, Conv, [128, 3, 1]], # [[-1, -3, -5, -6], 1, Concat, [1]], # [-1, 1, Conv, [512, 1, 1]], # 24 [-1, 3, GGhostRegNet, [96, 1]], # 12 [-1, 1, MP, []], [-1, 1, Conv, [96, 1, 1]], [-3, 1, Conv, [96, 1, 1]], [-1, 1, Conv, [96, 3, 2]], [[-1, -3], 1, Concat, [1]], # 29-P4/16 [-1, 1, Conv, [240, 1, 1]], # [-2, 1, Conv, [256, 1, 1]], # [-1, 1, Conv, [256, 3, 1]], # [-1, 1, Conv, [256, 3, 1]], # [-1, 1, Conv, [256, 3, 1]], # [-1, 1, Conv, [256, 3, 1]], # [[-1, -3, -5, -6], 1, Concat, [1]], # [-1, 1, Conv, [1024, 1, 1]], # 37 [-1, 5, GGhostRegNet, [240, 2]], # 19 [-1, 1, MP, []], [-1, 1, Conv, [240, 1, 1]], [-3, 1, Conv, [240, 1, 1]], [-1, 1, Conv, [240, 3, 2]], [[-1, -3], 1, Concat, [1]], # 42-P5/32 [-1, 1, Conv, [528, 1, 1]], # [-2, 1, Conv, [256, 1, 1]], # [-1, 1, Conv, [256, 3, 1]], # [-1, 1, Conv, [256, 3, 1]], # [-1, 1, Conv, [256, 3, 1]], # [-1, 1, Conv, [256, 3, 1]], # [[-1, -3, -5, -6], 1, Concat, [1]], # [-1, 1, Conv, [1024, 1, 1]], # 50 [-1, 7, GGhostRegNet, [528, 3]], # 26 ] # yolov7_MY head head: [[-1, 1, SPPCSPC, [512]], # 27 [-1, 1, Conv, [256, 1, 1]], [-1, 1, nn.Upsample, [None, 2, 'nearest']], [19, 1, Conv, [256, 1, 1]], # route backbone P4 [[-1, -2], 1, Concat, [1]], [-1, 1, Conv, [256, 1, 1]], [-2, 1, Conv, [256, 1, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], [-1, 1, Conv, [256, 1, 1]], # 39 [-1, 1, Conv, [128, 1, 1]], [-1, 1, nn.Upsample, [None, 2, 'nearest']], [12, 1, Conv, [128, 1, 1]], # route backbone P3 [[-1, -2], 1, Concat, [1]], [-1, 1, Conv, [128, 1, 1]], [-2, 1, Conv, [128, 1, 1]], [-1, 1, Conv, [64, 3, 1]], [-1, 1, Conv, [64, 3, 1]], [-1, 1, Conv, [64, 3, 1]], [-1, 1, Conv, [64, 3, 1]], [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], [-1, 1, Conv, [128, 1, 1]], # 51 [-1, 1, MP, []], [-1, 1, Conv, [128, 1, 1]], [-3, 1, Conv, [128, 1, 1]], [-1, 1, Conv, [128, 3, 2]], [[-1, -3, 39], 1, Concat, [1]], [-1, 1, Conv, [256, 1, 1]], [-2, 1, Conv, [256, 1, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [-1, 1, Conv, [128, 3, 1]], [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], [-1, 1, Conv, [256, 1, 1]], # 64 [-1, 1, MP, []], [-1, 1, Conv, [256, 1, 1]], [-3, 1, Conv, [256, 1, 1]], [-1, 1, Conv, [256, 3, 2]], [[-1, -3, 27], 1, Concat, [1]], [-1, 1, Conv, [512, 1, 1]], [-2, 1, Conv, [512, 1, 1]], [-1, 1, Conv, [256, 3, 1]], [-1, 1, Conv, [256, 3, 1]], [-1, 1, Conv, [256, 3, 1]], [-1, 1, Conv, [256, 3, 1]], [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]], [-1, 1, Conv, [512, 1, 1]], # 77 [51, 1, RepConv, [256, 3, 1]], [64, 1, RepConv, [512, 3, 1]], [77, 1, RepConv, [1024, 3, 1]], [[78,79,80], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5) ] 测试是否创建成功
这里是引用
