PyTorch 实现经典模型4：GoogLeNet

GoogLeNet

创新点：

通过多种卷积核叠加网络复杂性

学习多种卷积
提升计算效率

GoogLeNet网络深度达到22层

1x1卷积降低维度

降低计算量，提升计算效率

网络结构

代码

import torch
from torch import nnNUM_CLASSES = 10class BasicConv2d(nn.Module):def __init__(self, in_channels, out_channels, **kwargs):super(BasicConv2d, self).__init__()self.conv = nn.Conv2d(in_channels, out_channels, bias=False, **kwargs)self.bn = nn.BatchNorm2d(out_channels, eps=0.001)self.relu = nn.ReLU(inplace=True)def forward(self, x):x = self.conv(x)x = self.bn(x)x = self.relu(x)return xclass Inception(nn.Module):def __init__(self, in_channel, n1_1, n3x3red, n3x3, n5x5red, n5x5, pool_plane):super(Inception, self).__init__()# first lineself.branch1x1 = BasicConv2d(in_channel, n1_1, kernel_size=1)# second lineself.branch3x3 = nn.Sequential(BasicConv2d(in_channel, n3x3red, kernel_size=1),BasicConv2d(n3x3red, n3x3, kernel_size=3, padding=1))# third lineself.branch5x5 = nn.Sequential(BasicConv2d(in_channel, n5x5red, kernel_size=1),BasicConv2d(n5x5red, n5x5, kernel_size=5, padding=2))# fourth lineself.branch_pool = nn.Sequential(nn.MaxPool2d(3, stride=1, padding=1),BasicConv2d(in_channel, pool_plane, kernel_size=1))def forward(self, x):y1 = self.branch1x1(x)y2 = self.branch3x3(x)y3 = self.branch5x5(x)y4 = self.branch_pool(x)output = torch.cat([y1, y2, y3, y4], 1)return outputclass GoogLeNet(nn.Module):def __init__(self, num_classes=NUM_CLASSES):super(GoogLeNet, self).__init__()self.conv1 = BasicConv2d(3, 64, kernel_size=7, stride=2, padding=3)self.max_pool1 = nn.MaxPool2d(3, stride=2)self.conv2 = BasicConv2d(64, 192, kernel_size=3, stride=1, padding=1)self.max_pool2 = nn.MaxPool2d(3, stride=2)self.a3 = Inception(192, 64, 96, 128, 16, 32, 32)self.b3 = Inception(256, 128, 128, 192, 32, 96, 64)self.max_pool3 = nn.MaxPool2d(3, stride=2)self.a4 = Inception(480, 192, 96, 208, 16, 48, 64)self.b4 = Inception(512, 160, 112, 224, 24, 64, 64)self.c4 = Inception(512, 128, 128, 256, 24, 64, 64)self.d4 = Inception(512, 112, 144, 288, 32, 64, 64)self.e4 = Inception(528, 256, 160, 320, 32, 128, 128)self.max_pool4 = nn.MaxPool2d(3, stride=2)self.a5 = Inception(832, 256, 160, 320, 32, 128, 128)self.b5 = Inception(832, 384, 192, 384, 48, 128, 128)self.avg_pool = nn.AvgPool2d(7)self.dropout = nn.Dropout(0.4)self.classifier = nn.Linear(1024, num_classes)def forward(self, x):x = self.conv1(x)x = self.max_pool1(x)x = self.conv2(x)x = self.max_pool2(x)x = self.a3(x)x = self.b3(x)x = self.max_pool3(x)x = self.a4(x)x = self.b4(x)x = self.c4(x)x = self.d4(x)x = self.e4(x)x = self.max_pool4(x)x = self.a5(x)x = self.b5(x)x = self.avg_pool(x)x = self.dropout(x)x = x.view(x.size(0), -1)x = self.classifier(x)return x

Ref

Pytorch实现GoogLeNet解决各类数据集(cifar10/mnist/imagenet)分类
Pytorch实现GoogLeNet

PyTorch 实现经典模型4：GoogLeNet相关推荐

CNN经典模型：GoogLeNet（从Inception v1到v4的演进）
GoogLeNet和VGG是2014年ImageNet挑战赛(ILSVRC14)的双雄,GoogLeNet获得第一名.VGG获得第二名,这两类模型结构的共同特点是层次更深了.VGG继承了LeNet以及 ...
PyTorch 实现经典模型2：AlexNet
AlexNet 网络结构论文总结成功使用ReLU作为CNN的激活函数,并验证效果在较深的网络中超过了Sigmoid.成功解决了Sigmoid在网络较深时的梯度弥散问题. 训练时使用Dropout随 ...
PyTorch 实现经典模型3：VGG
VGG 网络结构代码 1) 导入必需的包 # 1) 导入必需的包 import torch import torch.nn as nn import torch.nn.functional as F ...
PyTorch 实现经典模型6：RCNN (Fast RCNN, Faster RCNN)
RCNN (Fast RCNN, Faster RCNN) 适用范围图像分类(Image classification) 目标检测(Object detection) 网络结构代码 Ref R-C ...
PyTorch 实现经典模型5：ResNet
ResNet 网络结构代码 #------------------------------用50行代码搭建ResNet---------------------------------------- ...
PyTorch 实现经典模型1：LeNet5
模型:LeNet5 网络结构符号说明网络参数代码实现 1) 导入必需的包 2) 搭建网络模型 3) 导入使用的数据集 4) 训练模型 5) 保存模型 6) 测试模型效果所遇错误 '_Incom ...
PyTorch 实现经典模型8：FCN
FCN 网络结构代码 class fcn(nn.Module):def __init__(self, num_classes):super(fcn, self).__init__()self.sta ...
PyTorch 实现经典模型7：YOLO (v1, v2, v3, v4)
YOLO (v1, v2, v3, v4) 网络结构 YOLO v3 网络结构代码 Ref <机器爱学习>YOLO v1深入理解 <机器爱学习>YOLOv2 / YOLO90 ...
动手学深度学习（二十二）——GoogLeNet：CNN经典模型（五）
文章目录 1. 含并行连结的网络(GoogLeNet) 1.1 Inception块 1.2 GoogLeNet模型 2. 动手实现简化的GoogLeNet模型 2.1 实现Inception块 2. ...

PyTorch 实现经典模型4：GoogLeNet

GoogLeNet

创新点：

网络结构

代码

Ref

PyTorch 实现经典模型4：GoogLeNet相关推荐

最新文章

热门文章