10_Advanced CNN_ResNet

传送门：11.卷积神经网络（高级篇）_哔哩哔哩_bilibili

利用残差结构块的网络

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。

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 ResidualBlock(nn.Module):
    def __init__(self, channels):
        super(ResidualBlock, self).__init__()
        self.channels = channels
        self.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 + 16
 
        self.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 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: %f %% ' % (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()

刘老师的话：

开发网络：

1.首先画出网络结构图，再去写代码

2.要有增量式开发的想法，就是说，一个一个层去实现，保证张量维度和手写计算的维度对应上
 

接下来的路：

1.深度学习的理论学习

2.阅读PyTorch的文档（通读文档）

3.复现经典论文（先读代码，尝试自己来写）

4.扩充视野，阅读新论文。知识上的盲点，技术上的盲点