YOLOv10全网最新创新点改进系列:融合GSConv+Slim Neck,双改进、双增强,替换特征融合层实现, 轻量化涨点改进策略,有效涨点神器!
所有改进代码均经过实验测试跑通!截止发稿时YOLOv10已改进40+!自己排列组合2-4种后,考虑位置不同后可排列组合上千万种!改进不重样!!专注AI学术,关注B站up主:Ai学术叫叫兽er!
购买相关资料后畅享一对一答疑!
# YOLOv10全网最新创新点改进系列:融合GSConv+Slim Neck,双改进、双增强,替换特征融合层实现, 轻量化涨点改进策略,有效涨点神器!
详细的改进教程以及源码,戳这!戳这!!戳这!!!B站:AI学术叫叫兽 源码在相簿的链接中,动态中也有链接,感谢支持!祝科研遥遥领先!
一、GSConv+Slim Neck概述
1.1 Slim Neck结构图
1.2 GSConv结构图
贡献:作者提出了一种新方法 GSConv 来减轻模型的复杂度并保持准确性。GSConv可以更好地平衡模型的准确性和速度。并且,提供了一种设计范式Slim Neck,以实现检测器更高的计算成本效益。
实验过程中,与原始网络相比,改进方法获得了最优秀的检测结果。
实验结果如图:
开始改进YOLOv8+GSConv+Slim Neck!
二、YOLOv10+GSConv+Slim Neck
2.1 修改YAML文件
# Ultralytics YOLO 🚀, AGPL-3.0 license
# YOLOv8 object detection model with P3-P5 outputs. For Usage examples see https://docs.ultralytics.com/tasks/detect# Parametersbackbone:# [from, repeats, module, args]- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4- [-1, 3, C2f, [128, True]]- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8- [-1, 6, C2f, [256, True]]- [-1, 1,GSConv, [512, 3, 2]] # 5-P4/16- [-1, 6, C2f, [512, True]]- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32- [-1, 3, C2f, [1024, True]]- [-1, 1, SPPF, [1024, 5]] # 9head:- [-1, 1, nn.Upsample, [None, 2, 'nearest']]- [[-1, 6], 1, Concat, [1]] # cat backbone P4- [-1, 3, VoVGSCSP, [512]] # 12- [-1, 1, nn.Upsample, [None, 2, 'nearest']]- [[-1, 4], 1, Concat, [1]] # cat backbone P3- [-1, 3, VoVGSCSP, [256]] # 15 (P3/8-small)- [-1, 1, Conv, [256, 3, 2]]- [[-1, 12], 1, Concat, [1]] # cat head P4- [-1, 3, VoVGSCSP, [512]] # 18 (P4/16-medium)- [-1, 1, Conv, [512, 3, 2]]- [[-1, 9], 1, Concat, [1]] # cat head P5- [-1, 3, VoVGSCSP, [1024]] # 21 (P5/32-large)- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)
在主干这里我只添加了一个GSConv模块,根据实验需要可以灵活配置(head同)!
2.2 新建SwinTransformer.py
核心代码示例如下:
class GSConv(nn.Module):# GSConv https://github.com/AlanLi1997/slim-neck-by-gsconvdef __init__(self, c1, c2, k=1, s=1, g=1, act=True):super().__init__()c_ = c2 // 2self.cv1 = Conv(c1, c_, k, s, None, g, 1, act)self.cv2 = Conv(c_, c_, 5, 1, None, c_, 1 , act)def forward(self, x):x1 = self.cv1(x)x2 = torch.cat((x1, self.cv2(x1)), 1)# shuffle# y = x2.reshape(x2.shape[0], 2, x2.shape[1] // 2, x2.shape[2], x2.shape[3])# y = y.permute(0, 2, 1, 3, 4)# return y.reshape(y.shape[0], -1, y.shape[3], y.shape[4])b, n, h, w = x2.data.size()b_n = b * n // 2y = 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 GSConvns(GSConv):# GSConv with a normative-shuffle https://github.com/AlanLi1997/slim-neck-by-gsconvdef __init__(self, c1, c2, k=1, s=1, g=1, act=True):super().__init__(c1, c2, k=1, s=1, g=1, act=True)c_ = c2 // 2self.shuf = nn.Conv2d(c_ * 2, c2, 1, 1, 0, bias=False)def forward(self, x):x1 = self.cv1(x)x2 = torch.cat((x1, self.cv2(x1)), 1)# normative-shuffle, TRT supportedreturn nn.ReLU(self.shuf(x2))class GSBottleneck(nn.Module):# GS Bottleneck https://github.com/AlanLi1997/slim-neck-by-gsconvdef __init__(self, c1, c2, k=3, s=1, e=0.5):super().__init__()c_ = int(c2*e)# for lightingself.conv_lighting = nn.Sequential(GSConv(c1, c_, 1, 1),GSConv(c_, c2, 3, 1, act=False))self.shortcut = Conv(c1, c2, 1, 1, act=False)def forward(self, x):return self.conv_lighting(x) + self.shortcut(x)class DWConv(Conv):# Depth-wise convolution classdef __init__(self, c1, c2, k=1, s=1, act=True): # ch_in, ch_out, kernel, stride, padding, groupssuper().__init__(c1, c2, k, s, g=math.gcd(c1, c2), act=act)class VoVGSCSP(nn.Module):# VoVGSCSP module with GSBottleneckdef __init__(self, cx, c2, n=1, shortcut=True, g=1, e=0.5):super().__init__()c_ = int(c2 * e) # hidden channelsself.cv1 = Conv(c1, c_, 1, 1)self.cv2 = Conv(c1, c_, 1, 1)# self.gc1 = GSConv(c_, c_, 1, 1)# self.gc2 = GSConv(c_, c_, 1, 1)# self.gsb = GSBottleneck(c_, c_, 1, 1)self.gsb = nn.Sequential(*(GSBottleneck(c_, c_, e=1.0) for _ in range(n)))self.res = Conv(c_, c_, 3, 1, act=False)self.cv3 = Conv(2 * c_, c2, 1) #def forward(self, x):x1 = self.gsb(self.cv1(x))y = self.cv2(x)return self.cv3(torch.cat((y, x1), dim=1))class VoVGSCSPC(VoVGSCSP):# cheap VoVGSCSP module with GSBottleneckdef __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):super().__init__(c1, c2)c_ = int(c2 * 0.5) # hidden channelsself.gsb = GSBottleneckC(c_, c_, 1, 1)
2.3 修改tasks.py
2.3.1 导包
from ultralytics.nn. SlimNeck import VoVGSCSP, VoVGSCSPC, GSConv
2.3.2 注册(包含很多改进,不需要的可删)
if m in (Classify, Conv, GGhostRegNet, ConvTranspose, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, Focus,BottleneckCSP, C1, C2, C2f, C3, C3TR, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x, RepC3, SEAttention,ContextAggregation, BoTNet, CBAM,LightConv,RepConv, SpatialAttention,Involution, CARAFE, VoVGSCSP, VoVGSCSPC,GSConv,HorBlock, SwinTransformer):
三、验证是否成功即可
执行命令
python train.py
示例如图:
改完收工!
关注B站:AI学术叫叫兽
从此走上科研快速路
遥遥领先同行!!!!
详细的改进教程以及源码,戳这!戳这!!戳这!!!B站:AI学术叫叫兽 源码在相簿的链接中,动态中也有链接,感谢支持!祝科研遥遥领先!
AI学术叫叫兽在这!家人们,给我遥遥领先!!!
[AI学术叫叫兽在这!家人们,给我遥遥领先!!!](https://space.bilibili.com/3546623938398505?plat_id=1&share_from=space&share_medium=android&share_plat=android&share_session_id=9ac46a33-0bcf-40d3-a9f8-3ff85e402116&share_source=COPY&share_tag=s_i&tim