YOLOv8目标检测创新改进与实战案例专栏
专栏目录： YOLOv8有效改进系列及项目实战目录 包含卷积，主干 注意力，检测头等创新机制 以及 各种目标检测分割项目实战案例
专栏链接: YOLOv8基础解析+创新改进+实战案例
介绍
摘要
基础模型的核心理念是“更多即不同”，这一理念在计算机视觉和自然语言处理领域取得了惊人的成功。然而，Transformer 模型的优化挑战和内在复杂性要求我们向简约的范式转变。在这项研究中，我们介绍了 VanillaNet，这是一种追求设计优雅的神经网络架构。通过避免高深度、捷径以及自注意等复杂操作，VanillaNet 展现出简洁明了却功能强大的特点。每一层都经过精心设计，结构紧凑且直观，训练后去除非线性激活函数以恢复原始架构。VanillaNet 克服了内在复杂性的挑战，非常适合资源受限的环境。其易于理解且高度简化的架构为高效部署开辟了新可能。大量实验表明，VanillaNet 的性能与著名的深度神经网络和视觉 Transformer 相媲美，展示了深度学习中极简主义的力量。VanillaNet 的这一创新旅程具有重新定义基础模型领域并挑战现状的巨大潜力，为优雅和有效的模型设计开辟了新路径。预训练模型和代码可在以下地址获得：https://github.com/huawei-noah/VanillaNet 和 https://gitee.com/mindspore/models/tree/master/research/cv/vanillanet。
文章链接
论文地址：论文地址
代码地址：代码地址
基本原理
简化的设计：VanillaNet避免了过度的深度、捷径和复杂的操作，如自注意力机制，使得网络结构变得简洁而强大。每一层都经过精心设计，紧凑而直观，训练后修剪非线性激活函数，以恢复原始架构[T5]。
网络架构：VanillaNet的架构包括三个主要部分：干细胞块（stem block）、主体和全连接层。主体通常包括四个阶段，每个阶段由堆叠相同的块构成。在每个阶段之后，特征的通道会扩展，而高度和宽度会减小[T3]。
训练策略：为了训练VanillaNet，研究人员进行了全面分析，针对简化的架构设计了“深度训练”策略。该策略从包含非线性激活函数的几层开始，随着训练的进行，逐渐消除这些非线性层，从而实现易于合并并保持推理速度。为增强网络的非线性，提出了一种高效的基于序列的激活函数，包含多个可学习的仿射变换[T4]。
实时处理性能：VanillaNet在实时处理方面表现出色，尤其是在图像分类任务中。通过调整通道数和池化大小，VanillaNet-13-1.5×在ImageNet上实现了83.11%的Top-1准确率，显示出VanillaNet在大规模图像分类任务中仍然具有强大的性能[T2]。
核心代码
class VanillaNet(nn.Module):
def __init__(self, in_chans=3, num_classes=1000, dims=[96, 192, 384, 768],
drop_rate=0, act_num=3, strides=[2,2,2,1], deploy=False, ada_pool=None, **kwargs):
super().__init__()
self.deploy = deploy
stride, padding = (4, 0) if not ada_pool else (3, 1)
if self.deploy:
self.stem = nn.Sequential(
nn.Conv2d(in_chans, dims[0], kernel_size=4, stride=stride, padding=padding),
activation(dims[0], act_num, deploy=self.deploy)
)
else:
self.stem1 = nn.Sequential(
nn.Conv2d(in_chans, dims[0], kernel_size=4, stride=stride, padding=padding),
nn.BatchNorm2d(dims[0], eps=1e-6),
)
self.stem2 = nn.Sequential(
nn.Conv2d(dims[0], dims[0], kernel_size=1, stride=1),
nn.BatchNorm2d(dims[0], eps=1e-6),
activation(dims[0], act_num)
)
self.act_learn = 1
self.stages = nn.ModuleList()
for i in range(len(strides)):
if not ada_pool:
stage = Block(dim=dims[i], dim_out=dims[i+1], act_num=act_num, stride=strides[i], deploy=deploy)
else:
stage = Block(dim=dims[i], dim_out=dims[i+1], act_num=act_num, stride=strides[i], deploy=deploy, ada_pool=ada_pool[i])
self.stages.append(stage)
self.depth = len(strides)
if self.deploy:
self.cls = nn.Sequential(
nn.AdaptiveAvgPool2d((1,1)),
nn.Dropout(drop_rate),
nn.Conv2d(dims[-1], num_classes, 1),
)
else:
self.cls1 = nn.Sequential(
nn.AdaptiveAvgPool2d((1,1)),
nn.Dropout(drop_rate),
nn.Conv2d(dims[-1], num_classes, 1),
nn.BatchNorm2d(num_classes, eps=1e-6),
)
self.cls2 = nn.Sequential(
nn.Conv2d(num_classes, num_classes, 1)
)
self.apply(self._init_weights)
def _init_weights(self, m):
if isinstance(m, (nn.Conv2d, nn.Linear)):
weight_init.trunc_normal_(m.weight, std=.02)
nn.init.constant_(m.bias, 0)
def change_act(self, m):
for i in range(self.depth):
self.stages[i].act_learn = m
self.act_learn = m
def forward(self, x):
if self.deploy:
x = self.stem(x)
else:
x = self.stem1(x)
x = torch.nn.functional.leaky_relu(x,self.act_learn)
x = self.stem2(x)
for i in range(self.depth):
x = self.stages[i](x)
if self.deploy:
x = self.cls(x)
else:
x = self.cls1(x)
x = torch.nn.functional.leaky_relu(x,self.act_learn)
x = self.cls2(x)
return x.view(x.size(0),-1)
def _fuse_bn_tensor(self, conv, bn):
kernel = conv.weight
bias = conv.bias
running_mean = bn.running_mean
running_var = bn.running_var
gamma = bn.weight
beta = bn.bias
eps = bn.eps
std = (running_var + eps).sqrt()
t = (gamma / std).reshape(-1, 1, 1, 1)
return kernel * t, beta + (bias - running_mean) * gamma / std
def switch_to_deploy(self):
self.stem2[2].switch_to_deploy()
kernel, bias = self._fuse_bn_tensor(self.stem1[0], self.stem1[1])
self.stem1[0].weight.data = kernel
self.stem1[0].bias.data = bias
kernel, bias = self._fuse_bn_tensor(self.stem2[0], self.stem2[1])
self.stem1[0].weight.data = torch.einsum('oi,icjk->ocjk', kernel.squeeze(3).squeeze(2), self.stem1[0].weight.data)
self.stem1[0].bias.data = bias + (self.stem1[0].bias.data.view(1,-1,1,1)*kernel).sum(3).sum(2).sum(1)
self.stem = torch.nn.Sequential(*[self.stem1[0], self.stem2[2]])
self.__delattr__('stem1')
self.__delattr__('stem2')
for i in range(self.depth):
self.stages[i].switch_to_deploy()
kernel, bias = self._fuse_bn_tensor(self.cls1[2], self.cls1[3])
self.cls1[2].weight.data = kernel
self.cls1[2].bias.data = bias
kernel, bias = self.cls2[0].weight.data, self.cls2[0].bias.data
self.cls1[2].weight.data = torch.matmul(kernel.transpose(1,3), self.cls1[2].weight.data.squeeze(3).squeeze(2)).transpose(1,3)
self.cls1[2].bias.data = bias + (self.cls1[2].bias.data.view(1,-1,1,1)*kernel).sum(3).sum(2).sum(1)
self.cls = torch.nn.Sequential(*self.cls1[0:3])
self.__delattr__('cls1')
self.__delattr__('cls2')
self.deploy = True
AI 代码解读
task与yaml配置
详见：https://blog.csdn.net/shangyanaf/article/details/139665923
