10_Advanced CNN_GoogLeNet

 传送门：11.卷积神经网络（高级篇）_哔哩哔哩_bilibili

目标：我们这里设计一种类GoogLeNet网络，主要实践inception

inception设计理念
卷积神经网络中，有很多超参数很难选（kernel_size等），那么我们就多用几种卷积，然后把结果摞在一起，将来的输出必定是效果好的卷积权重更大，那么结果也就会更好。在这几条路中自动找到最优。
四条路径下，必须保证图像的长度和高度一致

1*1的卷积有什么用？
改变通道数，减少计算量

 

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
import matplotlib.pyplot as plt

# prepare dataset
 
batch_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=r'D:\set', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root=r'D:\set', 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=1

class 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 + 16
 
        self.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 x
 
model = Net()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")  # 我只有一块cuda显卡
#print(torch.cuda.is_available())  # 检测一下GPU在不在
model.to(device)

# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
 
# training cycle forward, backward, update
 
def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        inputs, target = inputs.to(device), target.to(device)  # 迁移到GPU
        optimizer.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 = 0.0
 
 
def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            images, labels = images.to(device), labels.to(device)  # 迁移到GPU
            outputs = 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))
    return correct/total
 
if __name__ == '__main__':
    epoch_list = []
    acc_list = []
    
    for epoch in range(10):
        train(epoch)
        acc = test()
        epoch_list.append(epoch)
        acc_list.append(acc)
    
    plt.plot(epoch_list,acc_list)
    plt.ylabel('accuracy')
    plt.xlabel('epoch')
    plt.show()
 

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。