本文围绕八度卷积（OctConv）展开，解读其分离高低频特征图以降冗余的原理，并用PaddlePaddle复现OctConv及基于它的Oct-Mobilnetv1、OctResNet。在Cifar10数据集上实验，对比原模型，Oct版本参数量略增，训练精度相近，评估精度稍降，验证了其可行性。
☞☞☞AI 智能聊天, 问答助手, AI 智能搜索, 免费无限量使用 DeepSeek R1 模型☜☜☜
八度卷积于2019年在论文《Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convol》提出，在当时引起了不小的反响。八度卷积对传统的convolution进行改进，以降低空间冗余。其中“Drop an Octave”指降低八个音阶，代表频率减半。
不同于传统的卷积，八度卷积主要针对图像的高频信号与低频信号。首先，我们回忆一下数字图像处理中的高频信号与低频信号的概念。图像中的低频信号和高频信号也叫做低频分量和高频分量。图像中的高频分量，指的是图像强度（亮度/灰度）变化剧烈的像素点，例如边缘（轮廓）、图像的细节处、噪声（即噪点）（该点之所以称为噪点,是因为它与周边像素点灰度值有明显差别,也就是图像强度有剧烈的变化,所以噪声是高频部分）。图像中的低频分量，指的是图像强度（亮度/灰度）变换平缓的像素点，例如大片色块的地方。例如当我们在读书的时候，我们会聚焦于书上的文字而不是书纸本身，这里的文字就是高频分量，白纸即为低频分量。
下图是论文中给出的例子，左图是原图，中图表示低频信号，右图表示高频信号。
在论文中，作者提出较高的频率通常用精细的细节编码，较低的频率通常用全局结构编码。所以作者认为那么既然图像分为高低频，那么卷积产生的特征图自然也存在高低频之分。在图像处理中，模型通过高频特征图去学习图像包含的信息，因为它包含了轮廓、边缘等的信息，有助于进行显著性检测。相反，低频特征图包含的信息较少。如果我们用相同的处理方法来处理高频特征图和低频特征图，显然，前者的效益是远大于后者的。这就是特征图的冗余信息：包含信息较少的低频部分。所以在论文中作者提出了一种分而治之的方法，称之为Octave Feature Representation，对高频特征图与低频特征图分离开来进行处理。如下图所示，作者将低频特征图的分辨率降为1/2，这不仅有助于减少冗余数据，还有利于得到全局信息。
根据尺度空间理念，我们可以知道特征具有尺度不变性和旋转不变性。
为了同时做到同一频率内的更新和不同频率之间的交流，卷积核分成四部分：
下图直观地展示了八度卷积的卷积核，可以看出四个部分共同组成了大小为 k*k 的卷积核。其中，in和out分别表示输入和输出特征图的相关属性，在这篇文章中，输入的低频占比、通道数量都和输出的一致。
在了解了卷积核之后，下面介绍输入如何进行八度卷积操作得到输出结果。如下图所示，低频和高频的输入经过八度卷积操作得到了低频和高频的输出。红色表示高频，蓝色表示低频。绿色的箭头表示同一频率内的更新，红色的箭头表示不同频率之间的交流。
H和W分别表示特征图的长宽，可以看出低频特征图的长宽都是高频特征图的一半。因为分辨率不同，所以不同频率之间交流之前需要进行分辨率的调整：高频到低频需要进行池化（降采样）操作；低频到高频需要进行上采样操作。
import paddleimport paddle.nn as nnimport mathclass OctaveConv(nn.Layer):
def __init__(self, in_channels, out_channels, kernel_size, alpha_in=0.5, alpha_out=0.5, stride=1, padding=0, dilation=1,
groups=1, bias=False):
super(OctaveConv, self).__init__()
self.downsample = nn.AvgPool2D(kernel_size=(2, 2), stride=2)
self.upsample = nn.Upsample(scale_factor=2, mode='nearest') assert stride == 1 or stride == 2, "Stride should be 1 or 2."
self.stride = stride
self.is_dw = groups == in_channels assert 0 <= alpha_in <= 1 and 0 <= alpha_out <= 1, "Alphas should be in the interval from 0 to 1."
self.alpha_in, self.alpha_out = alpha_in, alpha_out
self.conv_l2l = None if alpha_in == 0 or alpha_out == 0 else \
nn.Conv2D(int(alpha_in * in_channels), int(alpha_out * out_channels),
kernel_size, 1, padding, dilation, math.ceil(alpha_in * groups))
self.conv_l2h = None if alpha_in == 0 or alpha_out == 1 or self.is_dw else \
nn.Conv2D(int(alpha_in * in_channels), out_channels - int(alpha_out * out_channels),
kernel_size, 1, padding, dilation, groups)
self.conv_h2l = None if alpha_in == 1 or alpha_out == 0 or self.is_dw else \
nn.Conv2D(in_channels - int(alpha_in * in_channels), int(alpha_out * out_channels),
kernel_size, 1, padding, dilation, groups)
self.conv_h2h = None if alpha_in == 1 or alpha_out == 1 else \
nn.Conv2D(in_channels - int(alpha_in * in_channels), out_channels - int(alpha_out * out_channels),
kernel_size, 1, padding, dilation, math.ceil(groups - alpha_in * groups)) def forward(self, x):
x_h, x_l = x if type(x) is tuple else (x, None)
x_h = self.downsample(x_h) if self.stride == 2 else x_h
x_h2h = self.conv_h2h(x_h)
x_h2l = self.conv_h2l(self.downsample(x_h)) if self.alpha_out > 0 and not self.is_dw else None
if x_l is not None:
x_l2l = self.downsample(x_l) if self.stride == 2 else x_l
x_l2l = self.conv_l2l(x_l2l) if self.alpha_out > 0 else None
if self.is_dw: return x_h2h, x_l2l else:
x_l2h = self.conv_l2h(x_l)
x_l2h = self.upsample(x_l2h) if self.stride == 1 else x_l2h
x_h = x_l2h + x_h2h
x_l = x_h2l + x_l2l if x_h2l is not None and x_l2l is not None else None
return x_h, x_l else: return x_h2h, x_h2lclass Conv_BN(nn.Layer):
def __init__(self, in_channels, out_channels, kernel_size, alpha_in=0.5, alpha_out=0.5, stride=1, padding=0, dilation=1,
groups=1, bias=False, norm_layer=nn.BatchNorm2D):
super(Conv_BN, self).__init__()
self.conv = OctaveConv(in_channels, out_channels, kernel_size, alpha_in, alpha_out, stride, padding, dilation,
groups, bias)
self.bn_h = None if alpha_out == 1 else norm_layer(int(out_channels * (1 - alpha_out)))
self.bn_l = None if alpha_out == 0 else norm_layer(int(out_channels * alpha_out)) def forward(self, x):
x_h, x_l = self.conv(x)
x_h = self.bn_h(x_h)
x_l = self.bn_l(x_l) if x_l is not None else None
return x_h, x_lclass Conv_BN_ACT(nn.Layer):
def __init__(self, in_channels=3, out_channels=32, kernel_size=3, alpha_in=0.5, alpha_out=0.5, stride=1, padding=0, dilation=1,
groups=1, bias=False, norm_layer=nn.BatchNorm2D, activation_layer=nn.ReLU):
super(Conv_BN_ACT, self).__init__()
self.conv = OctaveConv(in_channels, out_channels, kernel_size, alpha_in, alpha_out, stride, padding, dilation,
groups, bias)
self.bn_h = None if alpha_out == 1 else norm_layer(int(out_channels * (1 - alpha_out)))
self.bn_l = None if alpha_out == 0 else norm_layer(int(out_channels * alpha_out))
self.act = activation_layer() def forward(self, x):
x_h, x_l = self.conv(x)
x_h = self.act(self.bn_h(x_h))
x_l = self.act(self.bn_l(x_l)) if x_l is not None else None
return x_h, x_lOct-Mobilnetv1的复现即将Mobilnetv1中的原始的Conv2D替换为Oct-Conv，其他均保持不变，在后面打印了Oct-Mobilnetv1的网络结构以及参数量，方便大家查看。
# Oct-Mobilnetv1import paddle.nn as nn
__all__ = ['oct_mobilenet']def conv_bn(inp, oup, stride):
return nn.Sequential(
nn.Conv2D(inp, oup, 3, stride, 1),
nn.BatchNorm2D(oup),
nn.ReLU()
)def conv_dw(inp, oup, stride, alpha_in=0.5, alpha_out=0.5):
return nn.Sequential(
Conv_BN_ACT(inp, inp, kernel_size=3, stride=stride, padding=1, groups=inp, \
alpha_in=alpha_in, alpha_out=alpha_in if alpha_out != alpha_in else alpha_out),
Conv_BN_ACT(inp, oup, kernel_size=1, alpha_in=alpha_in, alpha_out=alpha_out)
)class OctMobileNet(nn.Layer):
def __init__(self, num_classes=1000):
super(OctMobileNet, self).__init__()
self.features = nn.Sequential(
conv_bn( 3, 32, 2),
conv_dw( 32, 64, 1, 0, 0.5),
conv_dw( 64, 128, 2),
conv_dw(128, 128, 1),
conv_dw(128, 256, 2),
conv_dw(256, 256, 1),
conv_dw(256, 512, 2),
conv_dw(512, 512, 1),
conv_dw(512, 512, 1),
conv_dw(512, 512, 1),
conv_dw(512, 512, 1),
conv_dw(512, 512, 1, 0.5, 0),
conv_dw(512, 1024, 2, 0, 0),
conv_dw(1024, 1024, 1, 0, 0),
)
self.avgpool = nn.AdaptiveAvgPool2D((1, 1))
self.fc = nn.Linear(1024, num_classes) def forward(self, x):
x_h, x_l = self.features(x)
x = self.avgpool(x_h)
x = x.reshape([-1, 1024])
x = self.fc(x) return xdef oct_mobilenet(**kwargs):
"""
Constructs a Octave MobileNet V1 model
"""
return OctMobileNet(**kwargs)Oct-ResNet的复现即将ResNet中的原始的Conv2D替换为Oct-Conv，其他均保持不变，在后面打印了Oct-ResNet的网络结构以及参数量，方便大家查看。
import paddle.nn as nn
__all__ = ['OctResNet', 'oct_resnet50', 'oct_resnet101', 'oct_resnet152', 'oct_resnet200']class Bottleneck(nn.Layer):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
base_width=64, alpha_in=0.5, alpha_out=0.5, norm_layer=None, output=False):
super(Bottleneck, self).__init__() if norm_layer is None:
norm_layer = nn.BatchNorm2D
width = int(planes * (base_width / 64.)) * groups # Both self.conv2 and self.downsample layers downsample the input when stride != 1
self.conv1 = Conv_BN_ACT(inplanes, width, kernel_size=1, alpha_in=alpha_in, alpha_out=alpha_out, norm_layer=norm_layer)
self.conv2 = Conv_BN_ACT(width, width, kernel_size=3, stride=stride, padding=1, groups=groups, norm_layer=norm_layer,
alpha_in=0 if output else 0.5, alpha_out=0 if output else 0.5)
self.conv3 = Conv_BN(width, planes * self.expansion, kernel_size=1, norm_layer=norm_layer,
alpha_in=0 if output else 0.5, alpha_out=0 if output else 0.5)
self.relu = nn.ReLU()
self.downsample = downsample
self.stride = stride def forward(self, x):
identity_h = x[0] if type(x) is tuple else x
identity_l = x[1] if type(x) is tuple else None
x_h, x_l = self.conv1(x)
x_h, x_l = self.conv2((x_h, x_l))
x_h, x_l = self.conv3((x_h, x_l)) if self.downsample is not None:
identity_h, identity_l = self.downsample(x)
x_h += identity_h
x_l = x_l + identity_l if identity_l is not None else None
x_h = self.relu(x_h)
x_l = self.relu(x_l) if x_l is not None else None
return x_h, x_lclass OctResNet(nn.Layer):
def __init__(self, block, layers, num_classes=1000, zero_init_residual=False,
groups=1, width_per_group=64, norm_layer=None):
super(OctResNet, self).__init__() if norm_layer is None:
norm_layer = nn.BatchNorm2D
self.inplanes = 64
self.groups = groups
self.base_width = width_per_group
self.conv1 = nn.Conv2D(3, self.inplanes, kernel_size=7, stride=2, padding=3,
)
self.bn1 = norm_layer(self.inplanes)
self.relu = nn.ReLU()
self.maxpool = nn.MaxPool2D(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0], norm_layer=norm_layer, alpha_in=0)
self.layer2 = self._make_layer(block, 128, layers[1], stride=2, norm_layer=norm_layer)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2, norm_layer=norm_layer)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2, norm_layer=norm_layer, alpha_out=0, output=True)
self.avgpool = nn.AdaptiveAvgPool2D((1, 1))
self.fc = nn.Linear(512 * block.expansion, num_classes) def _make_layer(self, block, planes, blocks, stride=1, alpha_in=0.5, alpha_out=0.5, norm_layer=None, output=False):
if norm_layer is None:
norm_layer = nn.BatchNorm2D
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
Conv_BN(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, alpha_in=alpha_in, alpha_out=alpha_out)
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample, self.groups,
self.base_width, alpha_in, alpha_out, norm_layer, output))
self.inplanes = planes * block.expansion for _ in range(1, blocks):
layers.append(block(self.inplanes, planes, groups=self.groups,
base_width=self.base_width, norm_layer=norm_layer,
alpha_in=0 if output else 0.5, alpha_out=0 if output else 0.5, output=output)) return nn.Sequential(*layers) def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x_h, x_l = self.layer1(x)
x_h, x_l = self.layer2((x_h,x_l))
x_h, x_l = self.layer3((x_h,x_l))
x_h, x_l = self.layer4((x_h,x_l))
x = self.avgpool(x_h)
x = x.reshape([x.shape[0], -1])
x = self.fc(x) return xdef oct_resnet50(pretrained=False, **kwargs):
"""Constructs a Octave ResNet-50 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = OctResNet(Bottleneck, [3, 4, 6, 3], **kwargs) return modeldef oct_resnet101(pretrained=False, **kwargs):
"""Constructs a Octave ResNet-101 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = OctResNet(Bottleneck, [3, 4, 23, 3], **kwargs) return modeldef oct_resnet152(pretrained=False, **kwargs):
"""Constructs a Octave ResNet-152 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = OctResNet(Bottleneck, [3, 8, 36, 3], **kwargs) return modeldef oct_resnet200(pretrained=False, **kwargs):
"""Constructs a Octave ResNet-200 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = OctResNet(Bottleneck, [3, 24, 36, 3], **kwargs) return model实验数据：Cifar10
CIFAR-10 是由 Hinton 的学生 Alex Krizhevsky 和 Ilya Sutskever 整理的一个用于识别普适物体的小型数据集。一共包含 10 个类别的 RGB 彩色图 片：飞机（ a叩lane ）、汽车（ automobile ）、鸟类（ bird ）、猫（ cat ）、鹿（ deer ）、狗（ dog ）、蛙类（ frog ）、马（ horse ）、船（ ship ）和卡车（ truck ）。图片的尺寸为 32×32 ，数据集中一共有 50000 张训练圄片和 10000 张测试图片。 CIFAR-10 的图片样例如图所示。
Octmobilnet_model = oct_mobilenet(num_classes=10)# inputs = paddle.randn((1, 2, 224, 224))# print(model(inputs))paddle.summary(Octmobilnet_model,(16,3,224,224))
import paddlefrom paddle.metric import Accuracyfrom paddle.vision.transforms import Compose, Normalize, Resize, Transpose, ToTensor
callback = paddle.callbacks.VisualDL(log_dir='visualdl_log_dir_octmobilenet')
normalize = Normalize(mean=[0.5, 0.5, 0.5],
std=[0.5, 0.5, 0.5],
data_format='HWC')
transform = Compose([ToTensor(), Normalize(), Resize(size=(224,224))])
cifar10_train = paddle.vision.datasets.Cifar10(mode='train',
transform=transform)
cifar10_test = paddle.vision.datasets.Cifar10(mode='test',
transform=transform)# 构建训练集数据加载器train_loader = paddle.io.DataLoader(cifar10_train, batch_size=768, shuffle=True, drop_last=True)# 构建测试集数据加载器test_loader = paddle.io.DataLoader(cifar10_test, batch_size=768, shuffle=True, drop_last=True)
Octmobilnet_model = paddle.Model(oct_mobilenet(num_classes=10))
optim = paddle.optimizer.Adam(learning_rate=0.001, parameters=Octmobilnet_model.parameters())
Octmobilnet_model.prepare(
optim,
paddle.nn.CrossEntropyLoss(),
Accuracy()
)
Octmobilnet_model.fit(train_data=train_loader,
eval_data=test_loader,
epochs=12,
callbacks=callback,
verbose=1
)from paddle.vision.models import MobileNetV1 mobile_model = MobileNetV1(num_classes=10)# inputs = paddle.randn((1, 2, 224, 224))# print(model(inputs))paddle.summary(mobile_model,(16,3,224,224))
import paddlefrom paddle.metric import Accuracyfrom paddle.vision.transforms import Compose, Normalize, Resize, Transpose, ToTensor
callback = paddle.callbacks.VisualDL(log_dir='visualdl_log_dir_mobilenet')
normalize = Normalize(mean=[0.5, 0.5, 0.5],
std=[0.5, 0.5, 0.5],
data_format='HWC')
transform = Compose([ToTensor(), Normalize(), Resize(size=(224,224))])
cifar10_train = paddle.vision.datasets.Cifar10(mode='train',
transform=transform)
cifar10_test = paddle.vision.datasets.Cifar10(mode='test',
transform=transform)# 构建训练集数据加载器train_loader = paddle.io.DataLoader(cifar10_train, batch_size=768, shuffle=True, drop_last=True)# 构建测试集数据加载器test_loader = paddle.io.DataLoader(cifar10_test, batch_size=768, shuffle=True, drop_last=True)
mobile_model = paddle.Model(MobileNetV1(num_classes=10))
optim = paddle.optimizer.Adam(learning_rate=0.001, parameters=mobile_model.parameters())
mobile_model.prepare(
optim,
paddle.nn.CrossEntropyLoss(),
Accuracy()
)
mobile_model.fit(train_data=train_loader,
eval_data=test_loader,
epochs=12,
callbacks=callback,
verbose=1
)octresnet50_model = oct_resnet50(num_classes=10) paddle.summary(octresnet50_model,(16,3,224,224))
import paddlefrom paddle.metric import Accuracyfrom paddle.vision.transforms import Compose, Normalize, Resize, Transpose, ToTensor
callback = paddle.callbacks.VisualDL(log_dir='visualdl_log_dir_octresnet')
normalize = Normalize(mean=[0.5, 0.5, 0.5],
std=[0.5, 0.5, 0.5],
data_format='HWC')
transform = Compose([ToTensor(), Normalize(), Resize(size=(224,224))])
cifar10_train = paddle.vision.datasets.Cifar10(mode='train',
transform=transform)
cifar10_test = paddle.vision.datasets.Cifar10(mode='test',
transform=transform)# 构建训练集数据加载器train_loader = paddle.io.DataLoader(cifar10_train, batch_size=256, shuffle=True, drop_last=True)# 构建测试集数据加载器test_loader = paddle.io.DataLoader(cifar10_test, batch_size=256, shuffle=True, drop_last=True)
oct_resnet50 = paddle.Model(oct_resnet50(num_classes=10))
optim = paddle.optimizer.Adam(learning_rate=0.001, parameters=oct_resnet50.parameters())
oct_resnet50.prepare(
optim,
paddle.nn.CrossEntropyLoss(),
Accuracy()
)
oct_resnet50.fit(train_data=train_loader,
eval_data=test_loader,
epochs=12,
callbacks=callback,
verbose=1
)import paddle# build modelresmodel = resnet50(num_classes=10) paddle.summary(resmodel,(16,3,224,224))
import paddlefrom paddle.metric import Accuracyfrom paddle.vision.transforms import Compose, Normalize, Resize, Transpose, ToTensorfrom paddle.vision.models import resnet50
callback = paddle.callbacks.VisualDL(log_dir='visualdl_log_dir_resnet')
normalize = Normalize(mean=[0.5, 0.5, 0.5],
std=[0.5, 0.5, 0.5],
data_format='HWC')
transform = Compose([ToTensor(), Normalize(), Resize(size=(224,224))])
cifar10_train = paddle.vision.datasets.Cifar10(mode='train',
transform=transform)
cifar10_test = paddle.vision.datasets.Cifar10(mode='test',
transform=transform)# 构建训练集数据加载器train_loader = paddle.io.DataLoader(cifar10_train, batch_size=256, shuffle=True, drop_last=True)# 构建测试集数据加载器test_loader = paddle.io.DataLoader(cifar10_test, batch_size=256, shuffle=True, drop_last=True)
res_model = paddle.Model(resnet50(num_classes=10))
optim = paddle.optimizer.Adam(learning_rate=0.001, parameters=res_model.parameters())
res_model.prepare(
optim,
paddle.nn.CrossEntropyLoss(),
Accuracy()
)
res_model.fit(train_data=train_loader,
eval_data=test_loader,
epochs=12,
callbacks=callback,
verbose=1
)本小节提供消融实验的结果以及可视化训练结果，共计包含四个实验，分别为octmobinetv1、mobinetv1、octresnet50以及resnet50在数据集Cifar10上的结果对比。
| model | epoch | train acc | eval acc | Total params |
|---|---|---|---|---|
| octmobinetv1 | 12 | 0.9609 | 0.6952 | 3253898 |
| mobinetv1 | 12 | 0.9488 | 0.7289 | 3239114 |
| model | epoch | train acc | eval acc | Total params |
|---|---|---|---|---|
| octresnet50 | 12 | 0.9613 | 0.7915 | 23625674 |
| resnet50 | 12 | 0.9524 | 0.7939 | 23581642 |
以上就是给你的神经网络降低一个八度：八度卷积飞桨版本复现的详细内容，更多请关注php中文网其它相关文章！
每个人都需要一台速度更快、更稳定的 PC。随着时间的推移，垃圾文件、旧注册表数据和不必要的后台进程会占用资源并降低性能。幸运的是，许多工具可以让 Windows 保持平稳运行。
Copyright 2014-2025 https://www.php.cn/ All Rights Reserved | php.cn | 湘ICP备2023035733号
759
收藏
