YOLOv5改进之YOLOv5+GSConv+Slim Neck

推荐

想亂叒偲箶 2024-02-06 14:21 2024/02/06 ©著作权读给你听

文章标签 GSConv Neck Slim 专栏分类人工智能 阅读数6849 评论数0 点赞数0 收藏数0

导读：论文题目 Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles 论文 ..

论文题目 Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles

论文 https://arxiv.org/abs/2206.02424

代码 https://github.com/AlanLi1997/Slim-neck-by-GSConv

直接步入正题~~~

目标为YOLOv5模型构建一个简单高效的Neck模块。考虑了卷积方法、特征融合结构、计算效率、计算成本效益等诸多因素。

一、GSConv

class GSConv(nn.Module): # GSConv https://github.com/AlanLi1997/slim-neck-by-gsconv def __init__(self, c1, c2, k 1, s 1, g 1, act True): super().__init__() c_ c2 // 2 self.cv1 Conv(c1, c_, k, s, None, g, act) self.cv2 Conv(c_, c_, 5, 1, None, c_, act) def forward(self, x): x1 self.cv1(x) x2 torch.cat((x1, self.cv2(x1)), 1) # shuffle b, n, h, w x2.data.size() b_n b * n // 2 y x2.reshape(b_n, 2, h * w) y y.permute(1, 0, 2) y y.reshape(2, -1, n // 2, h, w) return torch.cat((y[0], y[1]), 1)

将YOLOv5s.yaml的Neck模块中的Conv换成GSConv

1、将GSConv代码加入common.py文件中

2、找到yolo.py文件里的parse_model函数将类名加入进去

3、修改配置文件将YOLOv5s.yaml的Neck模块中的Conv换成GSConv

~~~此处有一个疑问官方给出的GSConv代码中为什么没用DWConv呢希望知道的朋友在评论区指点一下~~~

二、GSConv Slim Neck 1、GSBottleneck

class GSBottleneck(nn.Module): # GS Bottleneck https://github.com/AlanLi1997/slim-neck-by-gsconv def __init__(self, c1, c2, k 3, s 1): super().__init__() c_ c2 // 2 # for lighting self.conv_lighting nn.Sequential( GSConv(c1, c_, 1, 1), GSConv(c_, c2, 1, 1, act False)) # for receptive field self.conv nn.Sequential( GSConv(c1, c_, 3, 1), GSConv(c_, c2, 3, 1, act False)) self.shortcut Conv(c1, c2, 3, 1, act False) def forward(self, x): return self.conv_lighting(x) self.shortcut(x)

2、VoVGSCSP

class VoVGSCSP(nn.Module): # VoV-GSCSP https://github.com/AlanLi1997/slim-neck-by-gsconv def __init__(self, c1, c2, n 1, shortcut True, g 1, e 0.5): super().__init__() c_ int(c2 * e) self.cv1 Conv(c1, c_, 1, 1) self.cv2 Conv(2 * c_, c2, 1) self.m nn.Sequential(*(GSBottleneck(c_, c_) for _ in range(n))) def forward(self, x): x1 self.cv1(x) return self.cv2(torch.cat((self.m(x1), x1), dim 1))

将YOLOv5s.yaml的Neck模块中的Conv换成GSConv C3模块换为VoVGSCSP模块

1、将以下代码加入common.py文件中

class GSConv(nn.Module): # GSConv https://github.com/AlanLi1997/slim-neck-by-gsconv def __init__(self, c1, c2, k 1, s 1, g 1, act True): super().__init__() c_ c2 // 2 self.cv1 Conv(c1, c_, k, s, None, g, act) self.cv2 Conv(c_, c_, 5, 1, None, c_, act) def forward(self, x): x1 self.cv1(x) x2 torch.cat((x1, self.cv2(x1)), 1) # shuffle b, n, h, w x2.data.size() b_n b * n // 2 y x2.reshape(b_n, 2, h * w) y y.permute(1, 0, 2) y y.reshape(2, -1, n // 2, h, w) return torch.cat((y[0], y[1]), 1)class GSBottleneck(nn.Module): # GS Bottleneck https://github.com/AlanLi1997/slim-neck-by-gsconv def __init__(self, c1, c2, k 3, s 1): super().__init__() c_ c2 // 2 # for lighting self.conv_lighting nn.Sequential( GSConv(c1, c_, 1, 1), GSConv(c_, c2, 1, 1, act False)) # for receptive field self.conv nn.Sequential( GSConv(c1, c_, 3, 1), GSConv(c_, c2, 3, 1, act False)) self.shortcut nn.Identity() def forward(self, x): return self.conv_lighting(x)class VoVGSCSP(nn.Module): # VoV-GSCSP https://github.com/AlanLi1997/slim-neck-by-gsconv def __init__(self, c1, c2, n 1, shortcut True, g 1, e 0.5): super().__init__() c_ int(c2 * e) self.cv1 Conv(c1, c_, 1, 1) self.cv2 Conv(2 * c_, c2, 1) self.m nn.Sequential(*(GSBottleneck(c_, c_) for _ in range(n))) def forward(self, x): x1 self.cv1(x) return self.cv2(torch.cat((self.m(x1), x1), dim 1))

2、找到yolo.py文件里的parse_model函数将类名加入进去注意有两处需要添加的地方