1，本文介绍
本文将通过RCS-OSA改进YOLOv8：
-
RCS（重参数化卷积）：减少通道数以增强特征提取能力，同时在训练过程中学习深层表示，在推理时降低计算复杂度和内存消耗。
-
OSA（一次性聚合）：增加特征多样性，提高对不同尺度目标的检测性能，并优化计算效率。
该方法在YOLOv8中实现了这些机制，并提供了代码部署指南。
关于RCS-OSA的详细介绍可以看论文：https://arxiv.org/ftp/arxiv/papers/2307/2307.16412.pdf
本文将讲解如何将 RCS-OSA融合进yolov8
话不多说，上代码！
2， 将RCS-OSA融合进yolov8
2.1 步骤一
找到如下的目录'ultralytics/nn/modules'，然后在这个目录下创建一个RCSOSA.py文件，文件名字可以根据你自己的习惯起，然后将RCS-OSA的核心代码复制进去
import torch.nn as nn
import torch
import torch.nn.functional as F
import numpy as np
import math
# build RepVGG block
# -----------------------------
def conv_bn(in_channels, out_channels, kernel_size, stride, padding, groups=1):
result = nn.Sequential()
result.add_module('conv', nn.Conv2d(in_channels=in_channels, out_channels=out_channels,
kernel_size=kernel_size, stride=stride, padding=padding, groups=groups,
bias=False))
result.add_module('bn', nn.BatchNorm2d(num_features=out_channels))
return result
class SEBlock(nn.Module):
def __init__(self, input_channels):
super(SEBlock, self).__init__()
internal_neurons = input_channels // 8
self.down = nn.Conv2d(in_channels=input_channels, out_channels=internal_neurons, kernel_size=1, stride=1,
bias=True)
self.up = nn.Conv2d(in_channels=internal_neurons, out_channels=input_channels, kernel_size=1, stride=1,
bias=True)
self.input_channels = input_channels
def forward(self, inputs):
x = F.avg_pool2d(inputs, kernel_size=inputs.size(3))
x = self.down(x)
x = F.relu(x)
x = self.up(x)
x = torch.sigmoid(x)
x = x.view(-1, self.input_channels, 1, 1)
return inputs * x
class RepVGG(nn.Module):
def __init__(self, in_channels, out_channels, kernel_size=3,
stride=1, padding=1, dilation=1, groups=1, padding_mode='zeros', deploy=False, use_se=False):
super(RepVGG, self).__init__()
self.deploy = deploy
self.groups = groups
self.in_channels = in_channels
padding_11 = padding - kernel_size // 2
self.nonlinearity = nn.SiLU()
# self.nonlinearity = nn.ReLU()
if use_se:
self.se = SEBlock(out_channels, internal_neurons=out_channels // 16)
else:
self.se = nn.Identity()
if deploy:
self.rbr_reparam = nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size,
stride=stride,
padding=padding, dilation=dilation, groups=groups, bias=True,
padding_mode=padding_mode)
else:
self.rbr_identity = nn.BatchNorm2d(
num_features=in_channels) if out_channels == in_channels and stride == 1 else None
self.rbr_dense = conv_bn(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size,
stride=stride, padding=padding, groups=groups)
self.rbr_1x1 = conv_bn(in_channels=in_channels, out_channels=out_channels, kernel_size=1, stride=stride,
padding=padding_11, groups=groups)
# print('RepVGG Block, identity = ', self.rbr_identity)
def get_equivalent_kernel_bias(self):
kernel3x3, bias3x3 = self._fuse_bn_tensor(self.rbr_dense)
kernel1x1, bias1x1 = self._fuse_bn_tensor(self.rbr_1x1)
kernelid, biasid = self._fuse_bn_tensor(self.rbr_identity)
return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid
def _pad_1x1_to_3x3_tensor(self, kernel1x1):
if kernel1x1 is None:
return 0
else:
return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1])
def _fuse_bn_tensor(self, branch):
if branch is None:
return 0, 0
if isinstance(branch, nn.Sequential):
kernel = branch.conv.weight
running_mean = branch.bn.running_mean
running_var = branch.bn.running_var
gamma = branch.bn.weight
beta = branch.bn.bias
eps = branch.bn.eps
else:
assert isinstance(branch, nn.BatchNorm2d)
if not hasattr(self, 'id_tensor'):
input_dim = self.in_channels // self.groups
kernel_value = np.zeros((self.in_channels, input_dim, 3, 3), dtype=np.float32)
for i in range(self.in_channels):
kernel_value[i, i % input_dim, 1, 1] = 1
self.id_tensor = torch.from_numpy(kernel_value).to(branch.weight.device)
kernel = self.id_tensor
running_mean = branch.running_mean
running_var = branch.running_var
gamma = branch.weight
beta = branch.bias
eps = branch.eps
std = (running_var + eps).sqrt()
t = (gamma / std).reshape(-1, 1, 1, 1)
return kernel * t, beta - running_mean * gamma / std
def forward(self, inputs):
if hasattr(self, 'rbr_reparam'):
return self.nonlinearity(self.se(self.rbr_reparam(inputs)))
if self.rbr_identity is None:
id_out = 0
else:
id_out = self.rbr_identity(inputs)
return self.nonlinearity(self.se(self.rbr_dense(inputs) + self.rbr_1x1(inputs) + id_out))
def fusevggforward(self, x):
return self.nonlinearity(self.rbr_dense(x))
# RepVGG block end
# -----------------------------
class SR(nn.Module):
# Shuffle RepVGG
def __init__(self, c1, c2):
super().__init__()
c1_ = int(c1 // 2)
c2_ = int(c2 // 2)
self.repconv = RepVGG(c1_, c2_)
def forward(self, x):
x1, x2 = x.chunk(2, dim=1)
out = torch.cat((x1, self.repconv(x2)), dim=1)
out = self.channel_shuffle(out, 2)
return out
def channel_shuffle(self, x, groups):
batchsize, num_channels, height, width = x.data.size()
channels_per_group = num_channels // groups
x = x.view(batchsize, groups, channels_per_group, height, width)
x = torch.transpose(x, 1, 2).contiguous()
x = x.view(batchsize, -1, height, width)
return x
def make_divisible(x, divisor):
# Returns nearest x divisible by divisor
if isinstance(divisor, torch.Tensor):
divisor = int(divisor.max()) # to int
return math.ceil(x / divisor) * divisor
class RCSOSA(nn.Module):
# VoVNet with Res Shuffle RepVGG
def __init__(self, c1, c2, n=1, se=False, e=0.5, stackrep=True):
super().__init__()
n_ = n // 2
c_ = make_divisible(int(c1 * e), 8)
# self.conv1 = Conv(c1, c_)
self.conv1 = RepVGG(c1, c_)
self.conv3 = RepVGG(int(c_ * 3), c2)
self.sr1 = nn.Sequential(*[SR(c_, c_) for _ in range(n_)])
self.sr2 = nn.Sequential(*[SR(c_, c_) for _ in range(n_)])
self.se = None
if se:
self.se = SEBlock(c2)
def forward(self, x):
x1 = self.conv1(x)
x2 = self.sr1(x1)
x3 = self.sr2(x2)
x = torch.cat((x1, x2, x3), 1)
return self.conv3(x) if self.se is None else self.se(self.conv3(x))
if __name__ == '__main__':
m = RCSOSA(256, 256)
im = torch.randn(2, 256, 13, 13)
y = m(im)
print(y.shape)
2.2 步骤二
在task.py进行导入
2.3 步骤三
在task.py的parse_model中添加如下代码，需要在两个位置添加
到此注册成功,复制后面的yaml文件直接运行即可
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
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients, 79.3 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x summary: 365 layers, 68229648 parameters, 68229632 gradients, 258.5 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, RCSOSA, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, RCSOSA, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, RCSOSA, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, RCSOSA, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RCSOSA, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, 'nearest']]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, RCSOSA, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, RCSOSA, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, RCSOSA, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)
# 关于RCSOSA添加的位置大家可以自行调试,针对不同数据集位置不同,效果不同
不知不觉已经看完了哦，动动小手留个点赞吧--_--