目录

1.介绍

2. YOLOv5修改backbone为ConvNeXt

2.1修改common.py

2.2 修改yolo.py

2.3修改yolov5.yaml配置

1.介绍

• 论文地址：https://arxiv.org/abs/2201.03545
• 官方源代码地址：https://github.com/facebookresearch/ConvNeXt.git

自从ViT(Vision Transformer)在CV领域大放异彩，越来越多的研究人员开始拥入Transformer的怀抱。回顾近一年，在CV领域发的文章绝大多数都是基于Transformer的，比如2021年ICCV 的best paper Swin Transformer，而卷积神经网络已经开始慢慢淡出舞台中央。卷积神经网络要被Transformer取代了吗？也许会在不久的将来。今年(2022)一月份，Facebook AI Research和UC Berkeley一起发表了一篇文章A ConvNet for the 2020s，在文章中提出了ConvNeXt纯卷积神经网络，它对标的是2021年非常火的Swin Transformer，通过一系列实验比对，在相同的FLOPs下，ConvNeXt相比Swin Transformer拥有更快的推理速度以及更高的准确率，在ImageNet 22K上ConvNeXt-XL达到了87.8%的准确率，参看下图(原文表12)。看来ConvNeXt的提出强行给卷积神经网络续了口命。

ConvNeXt是一种由Facebook AI Research和UC Berkeley共同提出的卷积神经网络模型。它是一种纯卷积神经网络，由标准卷积神经网络模块构成，具有精度高、效率高、可扩展性强和设计非常简单的特点。ConvNeXt在2022年的CVPR上发表了一篇论文，题为“面向2020年代的卷积神经网络”。ConvNeXt已在ImageNet-1K和ImageNet-22K数据集上进行了训练，并在多个任务上取得了优异的表现。ConvNeXt的训练代码和预训练模型均已在GitHub上公开。
ConvNeXt是基于ResNet50进行改进的，其与Swin Transformer一样，具有4个Stage；不同的是ConvNeXt将各Stage中Block的数量比例从3：4：6：3改为了与Swin Transformer一样的1：1：3：1。 此外，在进行特征图降采样方面，ConvNeXt采用了与Swin Transformer一致的步长为4，尺寸为4×4的卷积核。
ConvNeXt的优点包括：
ConvNeXt是一种纯卷积神经网络，由标准卷积神经网络模块构成，具有精度高、效率高、可扩展性强和设计非常简单的特点。
ConvNeXt在ImageNet-1K和ImageNet-22K数据集上进行了训练，并在多个任务上取得了优异的表现。
ConvNeXt采用了Transformer网络的一些先进思想对现有的经典ResNet50/200网络做一些调整改进，将Transformer网络的最新的部分思想和技术引入到CNN网络现有的模块中从而结合这两种网络的优势，提高CNN网络的性能表现.
ConvNeXt的缺点包括：
ConvNeXt并没有在整体的网络框架和搭建思路上做重大的创新，它仅仅是依照Transformer网络的一些先进思想对现有的经典ResNet50/200网络做一些调整改进.
ConvNeXt相对于其他CNN模型而言，在某些情况下需要更多计算资源.

2. YOLOv5修改backbone为ConvNeXt

2.1修改common.py

将以下代码，添加进common.py。

############## ConvNext ##############
import torch.nn.functional as F
class LayerNorm_s(nn.Module):def __init__(self, normalized_shape, eps=1e-6, data_format="channels_last"):super().__init__()self.weight = nn.Parameter(torch.ones(normalized_shape))self.bias = nn.Parameter(torch.zeros(normalized_shape))self.eps = epsself.data_format = data_formatif self.data_format not in ["channels_last", "channels_first"]:raise NotImplementedErrorself.normalized_shape = (normalized_shape,)def forward(self, x):if self.data_format == "channels_last":return F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)elif self.data_format == "channels_first":u = x.mean(1, keepdim=True)s = (x - u).pow(2).mean(1, keepdim=True)x = (x - u) / torch.sqrt(s + self.eps)x = self.weight[:, None, None] * x + self.bias[:, None, None]return xclass ConvNextBlock(nn.Module):def __init__(self, dim, drop_path=0., layer_scale_init_value=1e-6):super().__init__()self.dwconv = nn.Conv2d(dim, dim, kernel_size=7, padding=3, groups=dim)  # depthwise convself.norm = LayerNorm_s(dim, eps=1e-6)self.pwconv1 = nn.Linear(dim, 4 * dim)self.act = nn.GELU()self.pwconv2 = nn.Linear(4 * dim, dim)self.gamma = nn.Parameter(layer_scale_init_value * torch.ones((dim)),requires_grad=True) if layer_scale_init_value > 0 else Noneself.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()def forward(self, x):input = xx = self.dwconv(x)x = x.permute(0, 2, 3, 1)  # (N, C, H, W) -> (N, H, W, C)x = self.norm(x)x = self.pwconv1(x)x = self.act(x)x = self.pwconv2(x)if self.gamma is not None:x = self.gamma * xx = x.permute(0, 3, 1, 2)  # (N, H, W, C) -> (N, C, H, W)x = input + self.drop_path(x)return xclass DropPath(nn.Module):"""Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks)."""def __init__(self, drop_prob=None):super(DropPath, self).__init__()self.drop_prob = drop_probdef forward(self, x):return drop_path_f(x, self.drop_prob, self.training)def drop_path_f(x, drop_prob: float = 0., training: bool = False):if drop_prob == 0. or not training:return xkeep_prob = 1 - drop_probshape = (x.shape[0],) + (1,) * (x.ndim - 1)  # work with diff dim tensors, not just 2D ConvNetsrandom_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)random_tensor.floor_()  # binarizeoutput = x.div(keep_prob) * random_tensorreturn outputclass CNeB(nn.Module):# CSP ConvNextBlock with 3 convolutions by iscyy/yoloairdef __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansionsuper().__init__()c_ = int(c2 * e)  # hidden channelsself.cv1 = Conv(c1, c_, 1, 1)self.cv2 = Conv(c1, c_, 1, 1)self.cv3 = Conv(2 * c_, c2, 1)self.m = nn.Sequential(*(ConvNextBlock(c_) for _ in range(n)))def forward(self, x):return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
############## ConvNext ##############

2.2 修改yolo.py

        if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, CNeB]:

2.3修改yolov5.yaml配置

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license# 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, CNeB, [128]],[-1, 1, Conv, [256, 3, 2]],  # 3-P3/8[-1, 6, CNeB, [256]],[-1, 1, Conv, [512, 3, 2]],  # 5-P4/16[-1, 9, CNeB, [512]],[-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32[-1, 3, CNeB, [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, CNeB, [256, False]],  # 17 (P3/8-small)[-1, 1, Conv, [256, 3, 2]],[[-1, 14], 1, Concat, [1]],  # cat head P4[-1, 3, CNeB, [512, False]],  # 20 (P4/16-medium)[-1, 1, Conv, [512, 3, 2]],[[-1, 10], 1, Concat, [1]],  # cat head P5[-1, 3, CNeB, [1024, False]],  # 23 (P5/32-large)[[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)]

后续会更新v7、v8版本