卷积神经网络(高级篇) Inception Moudel

Inception Moudel

1、卷积核超参数选择困难，自动找到卷积的最佳组合。

2、1x1卷积核，不同通道的信息融合。使用1x1卷积核虽然参数量增加了，但是能够显著的降低计算量(operations)

3、Inception Moudel由4个分支组成，要分清哪些是在Init里定义，哪些是在forward里调用。4个分支在dim=1(channels)上进行concatenate。24+16+24+24 = 88

4、GoogleNet的Inception(Pytorch实现)

代码说明：1、先使用类对Inception Moudel进行封装

2、先是1个卷积层(conv,maxpooling,relu)，然后inceptionA模块(输出的channels是24+16+24+24=88)，接下来又是一个卷积层(conv,mp,relu),然后inceptionA模块，最后一个全连接层(fc)。

3、1408这个数据可以通过x = x.view(in_size, -1)后调用x.shape得到。

import torch
import torch.nn as nn
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim# prepare datasetbatch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]) # 归一化,均值和方差train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using class
class InceptionA(nn.Module):def __init__(self, in_channels):super(InceptionA, self).__init__()self.branch1x1 = nn.Conv2d(in_channels, 16, kernel_size=1)self.branch5x5_1 = nn.Conv2d(in_channels, 16, kernel_size=1)self.branch5x5_2 = nn.Conv2d(16, 24, kernel_size=5, padding=2)self.branch3x3_1 = nn.Conv2d(in_channels, 16, kernel_size=1)self.branch3x3_2 = nn.Conv2d(16, 24, kernel_size=3, padding=1)self.branch3x3_3 = nn.Conv2d(24, 24, kernel_size=3, padding=1)self.branch_pool = nn.Conv2d(in_channels, 24, kernel_size=1)def forward(self, x):branch1x1 = self.branch1x1(x)branch5x5 = self.branch5x5_1(x)branch5x5 = self.branch5x5_2(branch5x5)branch3x3 = self.branch3x3_1(x)branch3x3 = self.branch3x3_2(branch3x3)branch3x3 = self.branch3x3_3(branch3x3)branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)branch_pool = self.branch_pool(branch_pool)outputs = [branch1x1, branch5x5, branch3x3, branch_pool]return torch.cat(outputs, dim=1) # b,c,w,h  c对应的是dim=1class Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = nn.Conv2d(1, 10, kernel_size=5)self.conv2 = nn.Conv2d(88, 20, kernel_size=5) # 88 = 24x3 + 16self.incep1 = InceptionA(in_channels=10) # 与conv1 中的10对应self.incep2 = InceptionA(in_channels=20) # 与conv2 中的20对应self.mp = nn.MaxPool2d(2)self.fc = nn.Linear(1408, 10) def forward(self, x):in_size = x.size(0)x = F.relu(self.mp(self.conv1(x)))x = self.incep1(x)x = F.relu(self.mp(self.conv2(x)))x = self.incep2(x)x = x.view(in_size, -1)x = self.fc(x)return xmodel = Net()# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch):running_loss = 0.0for batch_idx, data in enumerate(train_loader, 0):inputs, target = dataoptimizer.zero_grad()outputs = model(inputs)loss = criterion(outputs, target)loss.backward()optimizer.step()running_loss += loss.item()if batch_idx % 300 == 299:print('[%d, %5d] loss: %.3f' % (epoch+1, batch_idx+1, running_loss/300))running_loss = 0.0def test():correct = 0total = 0with torch.no_grad():for data in test_loader:images, labels = dataoutputs = model(images)_, predicted = torch.max(outputs.data, dim=1)total += labels.size(0)correct += (predicted == labels).sum().item()print('accuracy on test set: %d %% ' % (100*correct/total))if __name__ == '__main__':for epoch in range(10):train(epoch)test()

视频中截图：

说明：1、要解决的问题：梯度消失

2、跳连接，H(x) = F(x) + x,张量维度必须一样，加完后再激活。不要做pooling，张量的维度会发生变化。

代码说明：

1、先是1个卷积层(conv,maxpooling,relu)，然后ResidualBlock模块，接下来又是一个卷积层(conv,mp,relu),然后esidualBlock模块模块，最后一个全连接层(fc)。

import torch
import torch.nn as nn
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim# prepare datasetbatch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]) # 归一化,均值和方差train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using class
class ResidualBlock(nn.Module):def __init__(self, channels):super(ResidualBlock, self).__init__()self.channels = channelsself.conv1 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)self.conv2 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)def forward(self, x):y = F.relu(self.conv1(x))y = self.conv2(y)return F.relu(x + y)class Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = nn.Conv2d(1, 16, kernel_size=5)self.conv2 = nn.Conv2d(16, 32, kernel_size=5) # 88 = 24x3 + 16self.rblock1 = ResidualBlock(16)self.rblock2 = ResidualBlock(32)self.mp = nn.MaxPool2d(2)self.fc = nn.Linear(512, 10) # 暂时不知道1408咋能自动出来的def forward(self, x):in_size = x.size(0)x = self.mp(F.relu(self.conv1(x)))x = self.rblock1(x)x = self.mp(F.relu(self.conv2(x)))x = self.rblock2(x)x = x.view(in_size, -1)x = self.fc(x)return xmodel = Net()# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch):running_loss = 0.0for batch_idx, data in enumerate(train_loader, 0):inputs, target = dataoptimizer.zero_grad()outputs = model(inputs)loss = criterion(outputs, target)loss.backward()optimizer.step()running_loss += loss.item()if batch_idx % 300 == 299:print('[%d, %5d] loss: %.3f' % (epoch+1, batch_idx+1, running_loss/300))running_loss = 0.0def test():correct = 0total = 0with torch.no_grad():for data in test_loader:images, labels = dataoutputs = model(images)_, predicted = torch.max(outputs.data, dim=1)total += labels.size(0)correct += (predicted == labels).sum().item()print('accuracy on test set: %d %% ' % (100*correct/total))if __name__ == '__main__':for epoch in range(10):train(epoch)test()

卷积神经网络(高级篇) Inception Moudel相关推荐

PyTorch 深度学习实践 GPU版本B站刘二大人第11讲卷积神经网络(高级篇)GPU版本
第11讲卷积神经网络(高级篇) GPU版本源代码原理是基于B站刘二大人 :传送门PyTorch深度学习实践--卷积神经网络(高级篇) 这篇基于博主错错莫:传送门深度学习实践第11讲博文仅在 ...
循环神经网络-高级篇RNN Classifier
循环神经网络-高级篇RNN Classifier 本篇实现一个循环神经网络的分类器RNN Classifier 我们使用一个数据集包含Name,Country,其中名字有几千个,来自18个不同的国家, ...
必读论文 | 卷积神经网络百篇经典论文推荐
作为深度学习的代表算法之一,卷积神经网络(Convolutional Neural Networks,CNN)在计算机视觉.分类等领域上,都取得了当前最好的效果. 卷积神经网络的前世今生卷积神经网络 ...
霹雳巴拉卷积神经网络+图像分类篇
up给的教程路线:图像分类→目标检测→-一步步学习用pytorch实现深度学习在cv上的应用,并做笔记整理和总结. 参考内容来自: up主的b站链接:https://space.bilibili.co ...
【深度学习】人人都能看得懂的卷积神经网络——入门篇
近年来,卷积神经网络热度很高,在短时间内,这类网络成为了一种颠覆性技术,打破了从文本.视频到语音多个领域的大量最先进的算法,远远超出其最初在图像处理的应用范围. 卷积神经网络的一个例子在客流预测.信 ...
一维卷积神经网络_人人都能看得懂的卷积神经网络——入门篇
点击蓝字关注我们近年来,卷积神经网络热度很高,在短时间内,这类网络成为了一种颠覆性技术,打破了从文本.视频到语音多个领域的大量最先进的算法,远远超出其最初在图像处理的应用范围. 卷积神经网络的一个例 ...
Pytorch深度学习实践（b站刘二大人）P10讲 (CNN卷积神经网络基础篇)
1.全连接网络指的是网络里面用的都是线性层,如果一个网络全都由线性层串行连接起来,就叫做全连接网络在线性层里面输入和每一个输出值之间都存在权重,即每一个输入节点都要参与到下一层输出节点的计算上,这 ...
卷积神经网络(基础篇)
说明 0.前一部分叫做Feature Extraction,后一部分叫做classification 1.每一个卷积核它的通道数量要求和输入通道是一样的.这种卷积核的总数有多少个和你输出通道的数量是一 ...
用PyTorch搭建卷积神经网络
用PyTorch搭建卷积神经网络本篇是加拿大McGill本科,Waterloo硕士林羿实习时所作的工作.发文共享,主要是面对PyTorch的初学者. 本篇文章是一篇基础向的PyTorch教程,适合有 ...

卷积神经网络(高级篇) Inception Moudel

卷积神经网络(高级篇) Inception Moudel相关推荐

最新文章

热门文章