【YOLOv5/v7改进系列】引入RT-DETR的RepC3

一、导言

RT-DETR(Real-Time Detection Transformer)是一种针对实时目标检测任务的创新方法,它旨在克服YOLO系列和其他基于Transformer的检测器存在的局限性。RT-DETR的主要优点包括:

  1. 无NMS(非极大值抑制)优势:传统的YOLO系列检测器的性能受到NMS过程的负面影响,而RT-DETR利用端到端Transformer架构,消除了对NMS的依赖,从而提高了效率和准确性。

  2. 高效混合编码器:设计了一种高效的混合编码器,通过解耦处理多尺度特征的内部尺度交互和跨尺度融合,大大提升了处理速度。这种方法能够快速高效地处理来自不同尺度的信息,同时保持了准确性。

  3. 不确定性最小化查询选择:提出了一个创新的查询选择机制,旨在提供高质量的初始查询给解码器,从而提升检测的准确性。这个机制通过显式优化不确定性来避免选择具有低定位置信度的特征作为对象查询,减少了检测结果的不确定性。

  4. 灵活的速度调节:RT-DETR支持通过简单调整解码器层数的方式来适应不同场景下的速度需求,无需重新训练模型,为实际应用提供了极大的灵活性。

  5. 卓越的性能:在COCO数据集上,RT-DETR-R50和RT-DETR-R101分别达到了53.1%和54.3%的平均精度(AP),同时在T4 GPU上分别实现了108和74的帧每秒(FPS)。这不仅超越了先前的先进YOLO模型,还在速度和准确性上都优于DINO-R50,且在FPS上快约21倍。

  6. 预训练增强性能:经过Objects365数据集的预训练后,RT-DETR-R50和RT-DETR-R101的性能进一步提升至55.3%和56.2%的AP,显示了巨大的性能提升潜力。

  7. 技术扩展性:RT-DETR及其模型缩放策略拓宽了实时目标检测的技术路径,为多样化实时应用场景提供了超越YOLO的新可能性。

综上,RT-DETR通过其创新的设计,在保证实时性的前提下,实现了速度与准确性的优化,为实时目标检测领域带来了一种新的、性能优越的解决方案。

二、RepC3的特点
RepC3 类

RepC3是基于RepConv构建的一个模块,它是CSP(Cross Stage Partial)结构的一个变体,常用于神经网络的瓶颈层。主要特性包括:

  • 残差连接:类似于ResNet中的残差结构,RepC3通过cv1和cv2路径与中间的多层RepConv模块相加,形成残差连接,有助于梯度传播,加快训练速度,提高模型收敛性。
  • 高效计算:通过多个连续的RepConv模块,以较少的计算资源实现更强的表达能力。每个RepConv模块内部的两个分支在训练时提供多样性,而融合后的结构在推理时保持高效。
  • 通道缩放:引入了膨胀因子e,允许对中间通道数进行动态调整,以平衡模型的深度和宽度,优化模型的计算成本和表示能力。
总结优点
  • 高效推理:通过融合技术和残差结构,RepC3模块在保持高性能的同时,优化了模型的推理速度,特别适合于实时目标检测任务。
  • 灵活性与可扩展性:模块化的设计允许根据需要调整网络的深度和宽度,为不同任务和资源限制提供了高度的定制化能力。
  • 性能与计算效率的平衡:通过精细的结构设计,RepC3能够以较低的计算成本实现较高的检测精度,这对于实时应用至关重要。
三、准备工作

首先在YOLOv5/v7的models文件夹下新建文件repc3.py,导入如下代码

from models.common import *


class RepConv(nn.Module):
    """
    RepConv is a basic rep-style block, including training and deploy status.

    This module is used in RT-DETR.
    Based on https://github.com/DingXiaoH/RepVGG/blob/main/repvgg.py
    """
    default_act = nn.SiLU()  # default activation

    def __init__(self, c1, c2, k=3, s=1, p=1, g=1, d=1, act=True, bn=False, deploy=False):
        """Initializes Light Convolution layer with inputs, outputs & optional activation function."""
        super().__init__()
        assert k == 3 and p == 1
        self.g = g
        self.c1 = c1
        self.c2 = c2
        self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity()

        self.bn = nn.BatchNorm2d(num_features=c1) if bn and c2 == c1 and s == 1 else None
        self.conv1 = Conv(c1, c2, k, s, p=p, g=g, act=False)
        self.conv2 = Conv(c1, c2, 1, s, p=(p - k // 2), g=g, act=False)

    def forward_fuse(self, x):
        """Forward process."""
        return self.act(self.conv(x))

    def forward(self, x):
        """Forward process."""
        id_out = 0 if self.bn is None else self.bn(x)
        return self.act(self.conv1(x) + self.conv2(x) + id_out)

    def get_equivalent_kernel_bias(self):
        """Returns equivalent kernel and bias by adding 3x3 kernel, 1x1 kernel and identity kernel with their biases."""
        kernel3x3, bias3x3 = self._fuse_bn_tensor(self.conv1)
        kernel1x1, bias1x1 = self._fuse_bn_tensor(self.conv2)
        kernelid, biasid = self._fuse_bn_tensor(self.bn)
        return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid

    def _pad_1x1_to_3x3_tensor(self, kernel1x1):
        """Pads a 1x1 tensor to a 3x3 tensor."""
        if kernel1x1 is None:
            return 0
        else:
            return torch.nn.functional.pad(kernel1x1, [1, 1, 1, 1])

    def _fuse_bn_tensor(self, branch):
        """Generates appropriate kernels and biases for convolution by fusing branches of the neural network."""
        if branch is None:
            return 0, 0
        if isinstance(branch, Conv):
            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
        elif isinstance(branch, nn.BatchNorm2d):
            if not hasattr(self, 'id_tensor'):
                input_dim = self.c1 // self.g
                kernel_value = np.zeros((self.c1, input_dim, 3, 3), dtype=np.float32)
                for i in range(self.c1):
                    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 fuse_convs(self):
        """Combines two convolution layers into a single layer and removes unused attributes from the class."""
        if hasattr(self, 'conv'):
            return
        kernel, bias = self.get_equivalent_kernel_bias()
        self.conv = nn.Conv2d(in_channels=self.conv1.conv.in_channels,
                              out_channels=self.conv1.conv.out_channels,
                              kernel_size=self.conv1.conv.kernel_size,
                              stride=self.conv1.conv.stride,
                              padding=self.conv1.conv.padding,
                              dilation=self.conv1.conv.dilation,
                              groups=self.conv1.conv.groups,
                              bias=True).requires_grad_(False)
        self.conv.weight.data = kernel
        self.conv.bias.data = bias
        for para in self.parameters():
            para.detach_()
        self.__delattr__('conv1')
        self.__delattr__('conv2')
        if hasattr(self, 'nm'):
            self.__delattr__('nm')
        if hasattr(self, 'bn'):
            self.__delattr__('bn')
        if hasattr(self, 'id_tensor'):
            self.__delattr__('id_tensor')


class RepC3(nn.Module):
    """Rep C3."""

    def __init__(self, c1, c2, n=3, e=1.0):
        """Initialize CSP Bottleneck with a single convolution using input channels, output channels, and number."""
        super().__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c1, c_, 1, 1)
        self.m = nn.Sequential(*[RepConv(c_, c_) for _ in range(n)])
        self.cv3 = Conv(c_, c2, 1, 1) if c_ != c2 else nn.Identity()

    def forward(self, x):
        """Forward pass of RT-DETR neck layer."""
        return self.cv3(self.m(self.cv1(x)) + self.cv2(x))

其次在在YOLOv5/v7项目文件下的models/yolo.py中在文件首部添加代码

from models.repc3 import RepC3

并搜索def parse_model(d, ch)

定位到如下行添加以下代码

RepC3, 

四、YOLOv7-tiny改进工作

完成二后,在YOLOv7项目文件下的models文件夹下创建新的文件yolov7-tiny-repc3.yaml,导入如下代码。

# parameters
nc: 80  # number of classes
depth_multiple: 1.0  # model depth multiple
width_multiple: 1.0  # layer channel multiple

# anchors
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

# yolov7-tiny backbone
backbone:
  # [from, number, module, args] c2, k=1, s=1, p=None, g=1, act=True
  [[-1, 1, Conv, [32, 3, 2, None, 1, nn.LeakyReLU(0.1)]],  # 0-P1/2
  
   [-1, 1, Conv, [64, 3, 2, None, 1, nn.LeakyReLU(0.1)]],  # 1-P2/4
   
   [-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [[-1, -2, -3, -4], 1, Concat, [1]],
   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 7
   
   [-1, 1, MP, []],  # 8-P3/8
   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [[-1, -2, -3, -4], 1, Concat, [1]],
   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 14
   
   [-1, 1, MP, []],  # 15-P4/16
   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [[-1, -2, -3, -4], 1, Concat, [1]],
   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 21
   
   [-1, 1, MP, []],  # 22-P5/32
   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [[-1, -2, -3, -4], 1, Concat, [1]],
   [-1, 1, Conv, [512, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 28
  ]

# yolov7-tiny head
head:
  [[-1, 1, v7tiny_SPP, [256]], # 29
  
   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [21, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P4
   [[-1, -2], 1, Concat, [1]],
   
   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [[-1, -2, -3, -4], 1, Concat, [1]],
   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 39
  
   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [14, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P3
   [[-1, -2], 1, Concat, [1]],
   
   [-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [[-1, -2, -3, -4], 1, Concat, [1]],
   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 49
   
   [-1, 1, Conv, [128, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
   [[-1, 39], 1, Concat, [1]],
   
   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [[-1, -2, -3, -4], 1, Concat, [1]],
   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 57
   
   [-1, 1, Conv, [256, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
   [[-1, 29], 1, Concat, [1]],
   
   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [[-1, -2, -3, -4], 1, Concat, [1]],
   [-1, 3, RepC3, [256, 0.5]], # 65
      
   [49, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [57, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
   [65, 1, Conv, [512, 3, 1, None, 1, nn.LeakyReLU(0.1)]],

   [[66, 67, 68], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
  ]

                 from  n    params  module                                  arguments                     
  0                -1  1       928  models.common.Conv                      [3, 32, 3, 2, None, 1, LeakyReLU(negative_slope=0.1)]
  1                -1  1     18560  models.common.Conv                      [32, 64, 3, 2, None, 1, LeakyReLU(negative_slope=0.1)]
  2                -1  1      2112  models.common.Conv                      [64, 32, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
  3                -2  1      2112  models.common.Conv                      [64, 32, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
  4                -1  1      9280  models.common.Conv                      [32, 32, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
  5                -1  1      9280  models.common.Conv                      [32, 32, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
  6  [-1, -2, -3, -4]  1         0  models.common.Concat                    [1]                           
  7                -1  1      8320  models.common.Conv                      [128, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
  8                -1  1         0  models.common.MP                        []                            
  9                -1  1      4224  models.common.Conv                      [64, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 10                -2  1      4224  models.common.Conv                      [64, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 11                -1  1     36992  models.common.Conv                      [64, 64, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 12                -1  1     36992  models.common.Conv                      [64, 64, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 13  [-1, -2, -3, -4]  1         0  models.common.Concat                    [1]                           
 14                -1  1     33024  models.common.Conv                      [256, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 15                -1  1         0  models.common.MP                        []                            
 16                -1  1     16640  models.common.Conv                      [128, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 17                -2  1     16640  models.common.Conv                      [128, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 18                -1  1    147712  models.common.Conv                      [128, 128, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 19                -1  1    147712  models.common.Conv                      [128, 128, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 20  [-1, -2, -3, -4]  1         0  models.common.Concat                    [1]                           
 21                -1  1    131584  models.common.Conv                      [512, 256, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 22                -1  1         0  models.common.MP                        []                            
 23                -1  1     66048  models.common.Conv                      [256, 256, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 24                -2  1     66048  models.common.Conv                      [256, 256, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 25                -1  1    590336  models.common.Conv                      [256, 256, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 26                -1  1    590336  models.common.Conv                      [256, 256, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 27  [-1, -2, -3, -4]  1         0  models.common.Concat                    [1]                           
 28                -1  1    525312  models.common.Conv                      [1024, 512, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 29                -1  1    657408  models.common.v7tiny_SPP                [512, 256]                    
 30                -1  1     33024  models.common.Conv                      [256, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 31                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          
 32                21  1     33024  models.common.Conv                      [256, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 33          [-1, -2]  1         0  models.common.Concat                    [1]                           
 34                -1  1     16512  models.common.Conv                      [256, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 35                -2  1     16512  models.common.Conv                      [256, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 36                -1  1     36992  models.common.Conv                      [64, 64, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 37                -1  1     36992  models.common.Conv                      [64, 64, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 38  [-1, -2, -3, -4]  1         0  models.common.Concat                    [1]                           
 39                -1  1     33024  models.common.Conv                      [256, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 40                -1  1      8320  models.common.Conv                      [128, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 41                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          
 42                14  1      8320  models.common.Conv                      [128, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 43          [-1, -2]  1         0  models.common.Concat                    [1]                           
 44                -1  1      4160  models.common.Conv                      [128, 32, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 45                -2  1      4160  models.common.Conv                      [128, 32, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 46                -1  1      9280  models.common.Conv                      [32, 32, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 47                -1  1      9280  models.common.Conv                      [32, 32, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 48  [-1, -2, -3, -4]  1         0  models.common.Concat                    [1]                           
 49                -1  1      8320  models.common.Conv                      [128, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 50                -1  1     73984  models.common.Conv                      [64, 128, 3, 2, None, 1, LeakyReLU(negative_slope=0.1)]
 51          [-1, 39]  1         0  models.common.Concat                    [1]                           
 52                -1  1     16512  models.common.Conv                      [256, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 53                -2  1     16512  models.common.Conv                      [256, 64, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 54                -1  1     36992  models.common.Conv                      [64, 64, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 55                -1  1     36992  models.common.Conv                      [64, 64, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 56  [-1, -2, -3, -4]  1         0  models.common.Concat                    [1]                           
 57                -1  1     33024  models.common.Conv                      [256, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 58                -1  1    295424  models.common.Conv                      [128, 256, 3, 2, None, 1, LeakyReLU(negative_slope=0.1)]
 59          [-1, 29]  1         0  models.common.Concat                    [1]                           
 60                -1  1     65792  models.common.Conv                      [512, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 61                -2  1     65792  models.common.Conv                      [512, 128, 1, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 62                -1  1    147712  models.common.Conv                      [128, 128, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 63                -1  1    147712  models.common.Conv                      [128, 128, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 64  [-1, -2, -3, -4]  1         0  models.common.Concat                    [1]                           
 65                -1  1    657920  models.repc3.RepC3                      [512, 256, 3, 0.5]            
 66                49  1     73984  models.common.Conv                      [64, 128, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 67                57  1    295424  models.common.Conv                      [128, 256, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 68                65  1   1180672  models.common.Conv                      [256, 512, 3, 1, None, 1, LeakyReLU(negative_slope=0.1)]
 69      [66, 67, 68]  1     17132  models.yolo.IDetect                     [1, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]

Model Summary: 298 layers, 6541324 parameters, 6541324 gradients, 13.6 GFLOPS

运行后若打印出如上文本代表改进成功。

五、YOLOv5s改进工作

完成二后,在YOLOv5项目文件下的models文件夹下创建新的文件yolov5s-repc3.yaml,导入如下代码。

# Parameters
nc: 80  # 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, RepC3, [256, 0.5]],  # 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)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

                 from  n    params  module                                  arguments                     
  0                -1  1      3520  models.common.Conv                      [3, 32, 6, 2, 2]              
  1                -1  1     18560  models.common.Conv                      [32, 64, 3, 2]                
  2                -1  1     18816  models.common.C3                        [64, 64, 1]                   
  3                -1  1     73984  models.common.Conv                      [64, 128, 3, 2]               
  4                -1  2    115712  models.common.C3                        [128, 128, 2]                 
  5                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]              
  6                -1  3    625152  models.common.C3                        [256, 256, 3]                 
  7                -1  1   1180672  models.common.Conv                      [256, 512, 3, 2]              
  8                -1  1   1182720  models.common.C3                        [512, 512, 1]                 
  9                -1  1    656896  models.common.SPPF                      [512, 512, 5]                 
 10                -1  1    131584  models.common.Conv                      [512, 256, 1, 1]              
 11                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          
 12           [-1, 6]  1         0  models.common.Concat                    [1]                           
 13                -1  1    361984  models.common.C3                        [512, 256, 1, False]          
 14                -1  1     33024  models.common.Conv                      [256, 128, 1, 1]              
 15                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          
 16           [-1, 4]  1         0  models.common.Concat                    [1]                           
 17                -1  1     82688  models.repc3.RepC3                      [256, 128, 1, 0.5]            
 18                -1  1    147712  models.common.Conv                      [128, 128, 3, 2]              
 19          [-1, 14]  1         0  models.common.Concat                    [1]                           
 20                -1  1    296448  models.common.C3                        [256, 256, 1, False]          
 21                -1  1    590336  models.common.Conv                      [256, 256, 3, 2]              
 22          [-1, 10]  1         0  models.common.Concat                    [1]                           
 23                -1  1   1182720  models.common.C3                        [512, 512, 1, False]          
 24      [17, 20, 23]  1     16182  models.yolo.Detect                      [1, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]

Model Summary: 271 layers, 7014134 parameters, 7014134 gradients, 15.8 GFLOPs

运行后若打印出如上文本代表改进成功。

六、YOLOv5n改进工作

完成二后,在YOLOv5项目文件下的models文件夹下创建新的文件yolov5n-repc3.yaml,导入如下代码。

# Parameters
nc: 80  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.25  # 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, RepC3, [256, 0.5]],  # 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)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

                 from  n    params  module                                  arguments                     
  0                -1  1      1760  models.common.Conv                      [3, 16, 6, 2, 2]              
  1                -1  1      4672  models.common.Conv                      [16, 32, 3, 2]                
  2                -1  1      4800  models.common.C3                        [32, 32, 1]                   
  3                -1  1     18560  models.common.Conv                      [32, 64, 3, 2]                
  4                -1  2     29184  models.common.C3                        [64, 64, 2]                   
  5                -1  1     73984  models.common.Conv                      [64, 128, 3, 2]               
  6                -1  3    156928  models.common.C3                        [128, 128, 3]                 
  7                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]              
  8                -1  1    296448  models.common.C3                        [256, 256, 1]                 
  9                -1  1    164608  models.common.SPPF                      [256, 256, 5]                 
 10                -1  1     33024  models.common.Conv                      [256, 128, 1, 1]              
 11                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          
 12           [-1, 6]  1         0  models.common.Concat                    [1]                           
 13                -1  1     90880  models.common.C3                        [256, 128, 1, False]          
 14                -1  1      8320  models.common.Conv                      [128, 64, 1, 1]               
 15                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          
 16           [-1, 4]  1         0  models.common.Concat                    [1]                           
 17                -1  1     20864  models.repc3.RepC3                      [128, 64, 1, 0.5]             
 18                -1  1     36992  models.common.Conv                      [64, 64, 3, 2]                
 19          [-1, 14]  1         0  models.common.Concat                    [1]                           
 20                -1  1     74496  models.common.C3                        [128, 128, 1, False]          
 21                -1  1    147712  models.common.Conv                      [128, 128, 3, 2]              
 22          [-1, 10]  1         0  models.common.Concat                    [1]                           
 23                -1  1    296448  models.common.C3                        [256, 256, 1, False]          
 24      [17, 20, 23]  1      8118  models.yolo.Detect                      [1, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [64, 128, 256]]

Model Summary: 271 layers, 1763222 parameters, 1763222 gradients, 4.2 GFLOPs

运行后打印如上代码说明改进成功。

更多文章产出中,主打简洁和准确,欢迎关注我,共同探讨!

本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如若转载,请注明出处:/a/751690.html

如若内容造成侵权/违法违规/事实不符,请联系我们进行投诉反馈qq邮箱809451989@qq.com,一经查实,立即删除!

相关文章

GGUF模型转换入门

一、定义 1 定义 2 案例 二、实现 定义 GGUF是一种大模型文件格式,由开发者Georgi Gerganov提出。 这是一种针对大规模机器学习模型设计的二进制格式文件规范。它的主要优势在于能够将原始的大模型预训练结果经过特定优化后转换成这种格式,从而可以更…

UI Toolkit系统学习

UI Toolkit 此文章用于学习UnityUI系统,手头的项目做完会来完善 官方文档 Unity上方菜单栏点击Window->UI Toolkit->Samples可以看UI Toolkit中的很多样例 使用 UI Toolkit 和 UI Builder 制作物品编辑器 在文件夹中右键->Create->UI Toolkit->Edi…

花卉寄售系统

摘 要 随着互联网的快速发展和普及,电子商务已经成为人们日常生活中不可或缺的一部分。在电子商务领域,花卉行业也逐渐崭露头角,成为一个具有巨大潜力的市场。传统的花卉销售模式通常是通过实体店面进行销售,这种模式存在着许多问…

Android开发系列(十二)Jetpack Compose之BottomSheet

BottomSheet 是 Android 中一个常用的 UI 组件,它通常用于显示从屏幕底部弹出的用户界面。Jetpack Compose 是 Android 中的一个全新 UI 工具包,它提供了一种声明式的方式来构建用户界面。Jetpack Compose 中也有一个名为 BottomSheet 的组件&#xff0c…

数据恢复篇:如何从 Mac 硬盘安全恢复丢失的文件

Mac RAID 阵列用于大存储。Mac RAID 上的数据丢失可能很复杂。一般来说,从 Mac RAID 硬盘恢复已删除的文件并不困难。但如果​​您想从 Mac RAID 硬盘恢复由于格式化、病毒感染、硬盘故障而丢失的文件,情况就会发生变化。您必须找到一个功能强大的 Mac R…

【ONLYOFFICE 8.1】的安装与使用——功能全面的 PDF 编辑器、幻灯片版式、优化电子表格的协作

🔥 个人主页:空白诗 文章目录 一、引言二、ONLYOFFICE 简介三、安装1. Windows/Mac 安装2. 文档开发者版安装安装前准备使用 Docker 安装使用 Linux 发行版安装配置 ONLYOFFICE 文档开发者版集成和开发 四、使用1. 功能全面的 PDF 编辑器PDF 查看和导航P…

题解(A~D)

这次vp的比赛,我感觉前四道题虽然一点算法也没有,但是就是很难去做,要用数学思维去处理 第五题终究还是没有尝试,只能说才疏学浅吧,我只能说全是数学 话不多说,一起来看题目 A. X Axis 题意:…

【Redis】Java操作Redis(Jedis客户端使用)

Redis不仅支持简单的键值存储,还提供了丰富的数据结构(如列表、哈希表、集合等)和强大的原子操作,使得它在存储和处理数据时非常高效。关于这些数据结构的学习可以学习下面的博客: 【Redis】String的常用命令及图解St…

JS(JavaScript)DOM操作的趣味案例

天行健,君子以自强不息;地势坤,君子以厚德载物。 每个人都有惰性,但不断学习是好好生活的根本,共勉! 文章均为学习整理笔记,分享记录为主,如有错误请指正,共同学习进步。…

业务境外系列(1)——玩转谷歌浏览器

最好用的浏览器之一,很多调试开发的标准版本。去官方下载安装,从其他渠道下载的,一般版本会落后一些,或者被内置了一些东西。下载地址:https://www.google.com/chrome/ 官网 ,这样安装的时候比较正常。 查看版本: c…

spring-boot-starter-json配置对象属性为空不显示

问题背景 在Spring Boot中使用spring-boot-starter-json&#xff08;通常是通过jackson实现的&#xff09;时&#xff0c;如果你希望在序列化对象时&#xff0c;如果某个属性为空&#xff0c;则不显示该属性&#xff0c;你可以使用JsonInclude注解来实现这一点。 pom.xml <…

cs与msf权限传递以及mimikatz抓取win2012明文密码

启动服务端 进入客户端 建立监听 制作脚本 客户端运行程序 主机上线 打开msf 调用handler模块 创建监听 11.cs->msf 传递会话 12.传参完成 msf->cs会话传递 抓取密码&#xff08;null&#xff09; 修改注册表 shell reg add "HKEY_LOC…

1982Springboot宠物美容院管理系统idea开发mysql数据库web结构java编程计算机网页源码maven项目

一、源码特点 springboot宠物美容院管理系统是一套完善的信息系统&#xff0c;结合springboot框架和bootstrap完成本系统&#xff0c;对理解JSP java编程开发语言有帮助系统采用springboot框架&#xff08;MVC模式开发&#xff09;&#xff0c;系 统具有完整的源代码和数据库…

[C#]基于opencvsharp实现15关键点人体姿态估计

数据集 正确选择数据集以对结果产生适当影响也是非常必要的。在此姿势检测中&#xff0c;模型在两个不同的数据集即COCO关键点数据集和MPII人类姿势数据集上进行了预训练。 1. COCO&#xff1a;COCO关键点数据集是一个多人2D姿势估计数据集&#xff0c;其中包含从Flickr收集的…

Redis集群(Clustering in Redis)工作机制详解

Redis集群工作机制详解 Redis 集群是用于提高 Redis 可扩展性和高可用性的解决方案。 维基百科&#xff1a;Scalability is the property of a system to handle a growing amount of work by adding resources to the system. 可扩展性是系统的一种允许通过增加系统资源来处…

Zookeeper:基于Zookeeper的分布式锁

一、Zookeeper分布式锁原理 二、Zookeeper JavaAPI操作 1、Curator介绍 Curator是Apache Zookeeper的Java客户端。常见的Zookeeper Java API&#xff1a; 原生Java API。ZkClient。Curator。 Curator项目目标是简化Zookeeper客户端的使用。Curator最初是Netfix研发的&#xf…

Python | Leetcode Python题解之第202题快乐数

题目&#xff1a; 题解&#xff1a; def isHappy(self, n: int) -> bool:cycle_members {4, 16, 37, 58, 89, 145, 42, 20}def get_next(number):total_sum 0while number > 0:number, digit divmod(number, 10)total_sum digit ** 2return total_sumwhile n ! 1 an…

【UE5.3】笔记5-蓝图类

什么是蓝图类&#xff1a;其实就是C类&#xff0c;只不过是UE封装好的且可以直接拖出来可视化使用。 如何创建蓝图类&#xff1f;蓝图类有哪些&#xff1f; 蓝图类分为基于关卡的&#xff0c;基于Actor的&#xff0c;基于组件Component的。 基于关卡的蓝图类 一个关卡只能有…

Python | Leetcode Python题解之第201题数字范围按位与

题目&#xff1a; 题解&#xff1a; class Solution:def rangeBitwiseAnd(self, m: int, n: int) -> int:while m < n:# 抹去最右边的 1n n & (n - 1)return n

【Python实战因果推断】4_因果效应异质性4

目录 Cumulative Gain Target Transformation Cumulative Gain 如果采用与累积效应曲线完全相同的逻辑&#xff0c;但将每个点乘以累积样本 Ncum/N&#xff0c;就会得到累积增益曲线。现在&#xff0c;即使曲线的起点具有最高的效果&#xff08;对于一个好的模型来说&#x…