YOLOv8改进 | 2023主干篇 | RepViT从视觉变换器（ViT）的视角重新审视CNN
2023-12-19 06:43:50
一、本文介绍
本文给大家来的改进机制是RepViT，用其替换我们整个主干网络，其是今年最新推出的主干网络，其主要思想是将轻量级视觉变换器（ViT）的设计原则应用于传统的轻量级卷积神经网络(CNN)。我将其替换整个YOLOv8的Backbone，实现了大幅度涨点。我对修改后的网络(我用的最轻量的版本)，在一个包含1000张图片包含大中小的检测目标的数据集上(共有20+类别)，进行训练测试，发现所有的目标上均有一定程度的涨点效果，下面我会附上基础版本和修改版本的训练对比图。
推荐指数：?????
专栏回顾：YOLOv8改进系列专栏——本专栏持续复习各种顶会内容——科研必备????
训练结果对比图->???
?
目录
二、RepViT基本原理
?
官方论文地址：?官方论文地址点击即可跳转
官方代码地址：?官方代码地址点击即可跳转
??
RepViT: Revisiting Mobile CNN From ViT Perspective 这篇论文探讨了如何改进轻量级卷积神经网络（CNN）以提高其在移动设备上的性能和效率。作者们发现，虽然轻量级视觉变换器（ViT）因其能够学习全局表示而表现出色，但轻量级CNN和轻量级ViT之间的架构差异尚未得到充分研究。因此，他们通过整合轻量级ViT的高效架构设计，逐步改进标准轻量级CNN（特别是MobileNetV3），从而创造了一系列全新的纯CNN模型，称为RepViT。这些模型在各种视觉任务上表现出色，比现有的轻量级ViT更高效。
其主要的改进机制包括：
-
结构性重组：通过结构性重组（Structural Re-parameterization, SR），引入多分支拓扑结构，以提高训练时的性能。
-
扩展比率调整：调整卷积层中的扩展比率，以减少参数冗余和延迟，同时提高网络宽度以增强模型性能。
-
宏观设计优化：对网络的宏观架构进行优化，包括早期卷积层的设计、更深的下采样层、简化的分类器，以及整体阶段比例的调整。
-
微观设计调整：在微观架构层面进行优化，包括卷积核大小的选择和压缩激励（SE）层的最佳放置。
这些创新机制共同推动了轻量级CNN的性能和效率，使其更适合在移动设备上使用，下面的是官方论文中的结构图，我们对其进行简单的分析。
?
这张图片是论文中的图3，展示了RepViT架构的总览。RepViT有四个阶段，输入图像的分辨率依次为
?
每个阶段的通道维度用 Ci? 表示，批处理大小用 B 表示。?
- Stem：用于预处理输入图像的模块。
- Stage1-4：每个阶段由多个RepViTBlock组成，以及一个可选的RepViTSEBlock，包含深度可分离卷积（3x3DW），1x1卷积，压缩激励模块（SE）和前馈网络（FFN）。每个阶段通过下采样减少空间维度。
- Pooling：全局平均池化层，用于减少特征图的空间维度。
- FC：全连接层，用于最终的类别预测。
?总结：大家可以将RepViT看成是MobileNet系列的改进版本
三、RepViT的核心代码?
下面的代码是整个RepViT的核心代码，其中有个版本，对应的GFLOPs也不相同，使用方式看章节四。
import torch.nn as nn
from timm.models.layers import SqueezeExcite
import torch
__all__ = ['repvit_m0_6','repvit_m0_9', 'repvit_m1_0', 'repvit_m1_1', 'repvit_m1_5', 'repvit_m2_3']
def _make_divisible(v, divisor, min_value=None):
"""
This function is taken from the original tf repo.
It ensures that all layers have a channel number that is divisible by 8
It can be seen here:
https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
:param v:
:param divisor:
:param min_value:
:return:
"""
if min_value is None:
min_value = divisor
new_v = max(min_value, int(v + divisor / 2) // divisor * divisor)
# Make sure that round down does not go down by more than 10%.
if new_v < 0.9 * v:
new_v += divisor
return new_v
class Conv2d_BN(torch.nn.Sequential):
def __init__(self, a, b, ks=1, stride=1, pad=0, dilation=1,
groups=1, bn_weight_init=1, resolution=-10000):
super().__init__()
self.add_module('c', torch.nn.Conv2d(
a, b, ks, stride, pad, dilation, groups, bias=False))
self.add_module('bn', torch.nn.BatchNorm2d(b))
torch.nn.init.constant_(self.bn.weight, bn_weight_init)
torch.nn.init.constant_(self.bn.bias, 0)
@torch.no_grad()
def fuse_self(self):
c, bn = self._modules.values()
w = bn.weight / (bn.running_var + bn.eps) ** 0.5
w = c.weight * w[:, None, None, None]
b = bn.bias - bn.running_mean * bn.weight / \
(bn.running_var + bn.eps) ** 0.5
m = torch.nn.Conv2d(w.size(1) * self.c.groups, w.size(
0), w.shape[2:], stride=self.c.stride, padding=self.c.padding, dilation=self.c.dilation,
groups=self.c.groups,
device=c.weight.device)
m.weight.data.copy_(w)
m.bias.data.copy_(b)
return m
class Residual(torch.nn.Module):
def __init__(self, m, drop=0.):
super().__init__()
self.m = m
self.drop = drop
def forward(self, x):
if self.training and self.drop > 0:
return x + self.m(x) * torch.rand(x.size(0), 1, 1, 1,
device=x.device).ge_(self.drop).div(1 - self.drop).detach()
else:
return x + self.m(x)
@torch.no_grad()
def fuse_self(self):
if isinstance(self.m, Conv2d_BN):
m = self.m.fuse_self()
assert (m.groups == m.in_channels)
identity = torch.ones(m.weight.shape[0], m.weight.shape[1], 1, 1)
identity = torch.nn.functional.pad(identity, [1, 1, 1, 1])
m.weight += identity.to(m.weight.device)
return m
elif isinstance(self.m, torch.nn.Conv2d):
m = self.m
assert (m.groups != m.in_channels)
identity = torch.ones(m.weight.shape[0], m.weight.shape[1], 1, 1)
identity = torch.nn.functional.pad(identity, [1, 1, 1, 1])
m.weight += identity.to(m.weight.device)
return m
else:
return self
class RepVGGDW(torch.nn.Module):
def __init__(self, ed) -> None:
super().__init__()
self.conv = Conv2d_BN(ed, ed, 3, 1, 1, groups=ed)
self.conv1 = torch.nn.Conv2d(ed, ed, 1, 1, 0, groups=ed)
self.dim = ed
self.bn = torch.nn.BatchNorm2d(ed)
def forward(self, x):
return self.bn((self.conv(x) + self.conv1(x)) + x)
@torch.no_grad()
def fuse_self(self):
conv = self.conv.fuse_self()
conv1 = self.conv1
conv_w = conv.weight
conv_b = conv.bias
conv1_w = conv1.weight
conv1_b = conv1.bias
conv1_w = torch.nn.functional.pad(conv1_w, [1, 1, 1, 1])
identity = torch.nn.functional.pad(torch.ones(conv1_w.shape[0], conv1_w.shape[1], 1, 1, device=conv1_w.device),
[1, 1, 1, 1])
final_conv_w = conv_w + conv1_w + identity
final_conv_b = conv_b + conv1_b
conv.weight.data.copy_(final_conv_w)
conv.bias.data.copy_(final_conv_b)
bn = self.bn
w = bn.weight / (bn.running_var + bn.eps) ** 0.5
w = conv.weight * w[:, None, None, None]
b = bn.bias + (conv.bias - bn.running_mean) * bn.weight / \
(bn.running_var + bn.eps) ** 0.5
conv.weight.data.copy_(w)
conv.bias.data.copy_(b)
return conv
class RepViTBlock(nn.Module):
def __init__(self, inp, hidden_dim, oup, kernel_size, stride, use_se, use_hs):
super(RepViTBlock, self).__init__()
assert stride in [1, 2]
self.identity = stride == 1 and inp == oup
assert (hidden_dim == 2 * inp)
if stride == 2:
self.token_mixer = nn.Sequential(
Conv2d_BN(inp, inp, kernel_size, stride, (kernel_size - 1) // 2, groups=inp),
SqueezeExcite(inp, 0.25) if use_se else nn.Identity(),
Conv2d_BN(inp, oup, ks=1, stride=1, pad=0)
)
self.channel_mixer = Residual(nn.Sequential(
# pw
Conv2d_BN(oup, 2 * oup, 1, 1, 0),
nn.GELU() if use_hs else nn.GELU(),
# pw-linear
Conv2d_BN(2 * oup, oup, 1, 1, 0, bn_weight_init=0),
))
else:
assert (self.identity)
self.token_mixer = nn.Sequential(
RepVGGDW(inp),
SqueezeExcite(inp, 0.25) if use_se else nn.Identity(),
)
self.channel_mixer = Residual(nn.Sequential(
# pw
Conv2d_BN(inp, hidden_dim, 1, 1, 0),
nn.GELU() if use_hs else nn.GELU(),
# pw-linear
Conv2d_BN(hidden_dim, oup, 1, 1, 0, bn_weight_init=0),
))
def forward(self, x):
return self.channel_mixer(self.token_mixer(x))
class RepViT(nn.Module):
def __init__(self, cfgs):
super(RepViT, self).__init__()
# setting of inverted residual blocks
self.cfgs = cfgs
# building first layer
input_channel = self.cfgs[0][2]
patch_embed = torch.nn.Sequential(Conv2d_BN(3, input_channel // 2, 3, 2, 1), torch.nn.GELU(),
Conv2d_BN(input_channel // 2, input_channel, 3, 2, 1))
layers = [patch_embed]
# building inverted residual blocks
block = RepViTBlock
for k, t, c, use_se, use_hs, s in self.cfgs:
output_channel = _make_divisible(c, 8)
exp_size = _make_divisible(input_channel * t, 8)
layers.append(block(input_channel, exp_size, output_channel, k, s, use_se, use_hs))
input_channel = output_channel
self.features = nn.ModuleList(layers)
self.width_list = [i.size(1) for i in self.forward(torch.randn(1, 3, 640, 640))]
def forward(self, x):
# x = self.features(x
results = [None, None, None, None]
temp = None
i = None
for index, f in enumerate(self.features):
x = f(x)
if index == 0:
temp = x.size(1)
i = 0
elif x.size(1) == temp:
results[i] = x
else:
temp = x.size(1)
i = i + 1
return results
def repvit_m0_6():
"""
Constructs a MobileNetV3-Large model
"""
cfgs = [
[3, 2, 40, 1, 0, 1],
[3, 2, 40, 0, 0, 1],
[3, 2, 80, 0, 0, 2],
[3, 2, 80, 1, 0, 1],
[3, 2, 80, 0, 0, 1],
[3, 2, 160, 0, 1, 2],
[3, 2, 160, 1, 1, 1],
[3, 2, 160, 0, 1, 1],
[3, 2, 160, 1, 1, 1],
[3, 2, 160, 0, 1, 1],
[3, 2, 160, 1, 1, 1],
[3, 2, 160, 0, 1, 1],
[3, 2, 160, 1, 1, 1],
[3, 2, 160, 0, 1, 1],
[3, 2, 160, 0, 1, 1],
[3, 2, 320, 0, 1, 2],
[3, 2, 320, 1, 1, 1],
]
model = RepViT(cfgs)
return model
def repvit_m0_9():
"""
Constructs a MobileNetV3-Large model
"""
cfgs = [
# k, t, c, SE, HS, s
[3, 2, 48, 1, 0, 1],
[3, 2, 48, 0, 0, 1],
[3, 2, 48, 0, 0, 1],
[3, 2, 96, 0, 0, 2],
[3, 2, 96, 1, 0, 1],
[3, 2, 96, 0, 0, 1],
[3, 2, 96, 0, 0, 1],
[3, 2, 192, 0, 1, 2],
[3, 2, 192, 1, 1, 1],
[3, 2, 192, 0, 1, 1],
[3, 2, 192, 1, 1, 1],
[3, 2, 192, 0, 1, 1],
[3, 2, 192, 1, 1, 1],
[3, 2, 192, 0, 1, 1],
[3, 2, 192, 1, 1, 1],
[3, 2, 192, 0, 1, 1],
[3, 2, 192, 1, 1, 1],
[3, 2, 192, 0, 1, 1],
[3, 2, 192, 1, 1, 1],
[3, 2, 192, 0, 1, 1],
[3, 2, 192, 1, 1, 1],
[3, 2, 192, 0, 1, 1],
[3, 2, 192, 0, 1, 1],
[3, 2, 384, 0, 1, 2],
[3, 2, 384, 1, 1, 1],
[3, 2, 384, 0, 1, 1]
]
model = RepViT(cfgs)
return model
def repvit_m1_0():
"""
Constructs a MobileNetV3-Large model
"""
cfgs = [
# k, t, c, SE, HS, s
[3, 2, 56, 1, 0, 1],
[3, 2, 56, 0, 0, 1],
[3, 2, 56, 0, 0, 1],
[3, 2, 112, 0, 0, 2],
[3, 2, 112, 1, 0, 1],
[3, 2, 112, 0, 0, 1],
[3, 2, 112, 0, 0, 1],
[3, 2, 224, 0, 1, 2],
[3, 2, 224, 1, 1, 1],
[3, 2, 224, 0, 1, 1],
[3, 2, 224, 1, 1, 1],
[3, 2, 224, 0, 1, 1],
[3, 2, 224, 1, 1, 1],
[3, 2, 224, 0, 1, 1],
[3, 2, 224, 1, 1, 1],
[3, 2, 224, 0, 1, 1],
[3, 2, 224, 1, 1, 1],
[3, 2, 224, 0, 1, 1],
[3, 2, 224, 1, 1, 1],
[3, 2, 224, 0, 1, 1],
[3, 2, 224, 1, 1, 1],
[3, 2, 224, 0, 1, 1],
[3, 2, 224, 0, 1, 1],
[3, 2, 448, 0, 1, 2],
[3, 2, 448, 1, 1, 1],
[3, 2, 448, 0, 1, 1]
]
model = RepViT(cfgs)
return model
def repvit_m1_1():
"""
Constructs a MobileNetV3-Large model
"""
cfgs = [
# k, t, c, SE, HS, s
[3, 2, 64, 1, 0, 1],
[3, 2, 64, 0, 0, 1],
[3, 2, 64, 0, 0, 1],
[3, 2, 128, 0, 0, 2],
[3, 2, 128, 1, 0, 1],
[3, 2, 128, 0, 0, 1],
[3, 2, 128, 0, 0, 1],
[3, 2, 256, 0, 1, 2],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 512, 0, 1, 2],
[3, 2, 512, 1, 1, 1],
[3, 2, 512, 0, 1, 1]
]
model = RepViT(cfgs)
return model
def repvit_m1_5():
"""
Constructs a MobileNetV3-Large model
"""
cfgs = [
# k, t, c, SE, HS, s
[3, 2, 64, 1, 0, 1],
[3, 2, 64, 0, 0, 1],
[3, 2, 64, 1, 0, 1],
[3, 2, 64, 0, 0, 1],
[3, 2, 64, 0, 0, 1],
[3, 2, 128, 0, 0, 2],
[3, 2, 128, 1, 0, 1],
[3, 2, 128, 0, 0, 1],
[3, 2, 128, 1, 0, 1],
[3, 2, 128, 0, 0, 1],
[3, 2, 128, 0, 0, 1],
[3, 2, 256, 0, 1, 2],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 1, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 256, 0, 1, 1],
[3, 2, 512, 0, 1, 2],
[3, 2, 512, 1, 1, 1],
[3, 2, 512, 0, 1, 1],
[3, 2, 512, 1, 1, 1],
[3, 2, 512, 0, 1, 1]
]
model = RepViT(cfgs)
return model
def repvit_m2_3():
"""
Constructs a MobileNetV3-Large model
"""
cfgs = [
# k, t, c, SE, HS, s
[3, 2, 80, 1, 0, 1],
[3, 2, 80, 0, 0, 1],
[3, 2, 80, 1, 0, 1],
[3, 2, 80, 0, 0, 1],
[3, 2, 80, 1, 0, 1],
[3, 2, 80, 0, 0, 1],
[3, 2, 80, 0, 0, 1],
[3, 2, 160, 0, 0, 2],
[3, 2, 160, 1, 0, 1],
[3, 2, 160, 0, 0, 1],
[3, 2, 160, 1, 0, 1],
[3, 2, 160, 0, 0, 1],
[3, 2, 160, 1, 0, 1],
[3, 2, 160, 0, 0, 1],
[3, 2, 160, 0, 0, 1],
[3, 2, 320, 0, 1, 2],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 320, 1, 1, 1],
[3, 2, 320, 0, 1, 1],
# [3, 2, 320, 1, 1, 1],
# [3, 2, 320, 0, 1, 1],
[3, 2, 320, 0, 1, 1],
[3, 2, 640, 0, 1, 2],
[3, 2, 640, 1, 1, 1],
[3, 2, 640, 0, 1, 1],
# [3, 2, 640, 1, 1, 1],
# [3, 2, 640, 0, 1, 1]
]
model = RepViT(cfgs)
return model
四、手把手教你添加RepViT网络结构
这个主干的网络结构添加起来算是所有的改进机制里最麻烦的了，因为有一些网略结构可以用yaml文件搭建出来，有一些网络结构其中的一些细节根本没有办法用yaml文件去搭建，用yaml文件去搭建会损失一些细节部分(而且一个网络结构设计很多细节的结构修改方式都不一样，一个一个去修改大家难免会出错)，所以这里让网络直接返回整个网络，然后修改部分 yolo代码以后就都以这种形式添加了，以后我提出的网络模型基本上都会通过这种方式修改，我也会进行一些模型细节改进。创新出新的网络结构大家直接拿来用就可以的。下面开始添加教程->
(同时每一个后面都有代码，大家拿来复制粘贴替换即可，但是要看好了不要复制粘贴替换多了)
修改一
我们复制网络结构代码到“ultralytics/nn/modules”目录下创建一个py文件复制粘贴进去 ，我这里起的名字是RepViT。
?
修改二
找到如下的文件"ultralytics/nn/tasks.py" 在开始的部分导入我们的模型如下图。
?
from .modules.RepViT import repvit_m0_6, repvit_m0_9, repvit_m1_0, repvit_m1_1, repvit_m1_5, repvit_m2_3修改三?
添加如下两行代码！！！
?
修改四
找到七百多行大概把具体看图片，按照图片来修改就行，添加红框内的部分，注意没有()只是函数名。
?
elif m in {repvit_m0_6, repvit_m0_9, repvit_m1_0, repvit_m1_1, repvit_m1_5, repvit_m2_3}:
m = m()
c2 = m.width_list # 返回通道列表
backbone = True修改五?
下面的两个红框内都是需要改动的。?
?
if isinstance(c2, list):
m_ = m
m_.backbone = True
else:
m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
t = str(m)[8:-2].replace('__main__.', '') # module type
m.np = sum(x.numel() for x in m_.parameters()) # number params
m_.i, m_.f, m_.type = i + 4 if backbone else i, f, t # attach index, 'from' index, type修改六?
如下的也需要修改，全部按照我的来。
?
代码如下把原先的代码替换了即可。?
if verbose:
LOGGER.info(f'{i:>3}{str(f):>20}{n_:>3}{m.np:10.0f} {t:<45}{str(args):<30}') # print
save.extend(x % (i + 4 if backbone else i) for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
layers.append(m_)
if i == 0:
ch = []
if isinstance(c2, list):
ch.extend(c2)
if len(c2) != 5:
ch.insert(0, 0)
else:
ch.append(c2)修改七
修改七和前面的都不太一样，需要修改前向传播中的一个部分，?已经离开了parse_model方法了。
可以在图片中开代码行数，没有离开task.py文件都是同一个文件。 同时这个部分有好几个前向传播都很相似，大家不要看错了，是70多行左右的！！！，同时我后面提供了代码，大家直接复制粘贴即可，有时间我针对这里会出一个视频。
?
代码如下->
def _predict_once(self, x, profile=False, visualize=False):
"""
Perform a forward pass through the network.
Args:
x (torch.Tensor): The input tensor to the model.
profile (bool): Print the computation time of each layer if True, defaults to False.
visualize (bool): Save the feature maps of the model if True, defaults to False.
Returns:
(torch.Tensor): The last output of the model.
"""
y, dt = [], [] # outputs
for m in self.model:
if m.f != -1: # if not from previous layer
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
if profile:
self._profile_one_layer(m, x, dt)
if hasattr(m, 'backbone'):
x = m(x)
if len(x) != 5: # 0 - 5
x.insert(0, None)
for index, i in enumerate(x):
if index in self.save:
y.append(i)
else:
y.append(None)
x = x[-1] # 最后一个输出传给下一层
else:
x = m(x) # run
y.append(x if m.i in self.save else None) # save output
if visualize:
feature_visualization(x, m.type, m.i, save_dir=visualize)
return x到这里就完成了修改部分，但是这里面细节很多，大家千万要注意不要替换多余的代码，导致报错，也不要拉下任何一部，都会导致运行失败，而且报错很难排查！！！很难排查！！！?
修改八
这个Swin Transformer和其他的不太一样会导致计算的GFLOPs计算异常，所以需要额外修改一处，?我们找到如下文件'ultralytics/utils/torch_utils.py'按照如下的图片进行修改。
?
五、RepViT的yaml文件
复制如下yaml文件进行运行！！！?
# 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, repvit_m0_9, []] # 4
- [-1, 1, SPPF, [1024, 5]] # 5
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, 'nearest']] # 6
- [[-1, 3], 1, Concat, [1]] # 7 cat backbone P4
- [-1, 3, C2f, [512]] # 8
- [-1, 1, nn.Upsample, [None, 2, 'nearest']] # 9
- [[-1, 2], 1, Concat, [1]] # 10 cat backbone P3
- [-1, 3, C2f, [256]] # 11 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]] # 12
- [[-1, 8], 1, Concat, [1]] # 13 cat head P4
- [-1, 3, C2f, [512]] # 14 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]] # 15
- [[-1, 5], 1, Concat, [1]] # 16 cat head P5
- [-1, 3, C2f, [1024]] # 17 (P5/32-large)
- [[11, 14, 17], 1, Detect, [nc]] # Detect(P3, P4, P5)
六、成功运行记录?
下面是成功运行的截图，已经完成了有1个epochs的训练，图片太大截不全第2个epochs了。?
?
七、本文总结
到此本文的正式分享内容就结束了，在这里给大家推荐我的YOLOv8改进有效涨点专栏，本专栏目前为新开的平均质量分98分，后期我会根据各种最新的前沿顶会进行论文复现，也会对一些老的改进机制进行补充，目前本专栏免费阅读(暂时，大家尽早关注不迷路~)，如果大家觉得本文帮助到你了，订阅本专栏，关注后续更多的更新~
?
文章来源:https://blog.csdn.net/java1314777/article/details/135052550
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。 如若内容造成侵权/违法违规/事实不符，请联系我的编程经验分享网邮箱：veading@qq.com进行投诉反馈，一经查实，立即删除！
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。 如若内容造成侵权/违法违规/事实不符，请联系我的编程经验分享网邮箱：veading@qq.com进行投诉反馈，一经查实，立即删除！