深度学习笔记（2）——pytorch实现MNIST数据集分类（FNN、CNN、RNN、LSTM、GRU）

0 前言

快开学了，花了一个晚上时间复习深度学习基础代码，复习了最基础的MNIST手写数字识别数据集分类，使用FNN、CNN、RNN、LSTM、GRU实现。

1 数据预处理

import matplotlib.pyplot as plt
import torch
import time
import torch.nn.functional as F
from torch import nn, optim
from torchvision.datasets import MNIST
from torchvision.transforms import Compose, ToTensor, Normalize, Resize
from torch.utils.data import DataLoader
from sklearn.metrics import accuracy_score

# 超参数
BATCH_SIZE = 64  # 批次大小
EPOCHS = 5  # 迭代轮数
# 设备
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
# 数据转换
transformers = Compose(transforms=[ToTensor(), Normalize(mean=(0.1307,), std=(0.3081,))])
# 数据装载
dataset_train = MNIST(root=r'./data', train=True, download=False, transform=transformers)
dataset_test = MNIST(root=r'./data', train=False, download=False, transform=transformers)
dataloader_train = DataLoader(dataset=dataset_train, batch_size=BATCH_SIZE, shuffle=True)
dataloader_test = DataLoader(dataset=dataset_test, batch_size=BATCH_SIZE, shuffle=True)

2 FNN（前馈神经网络）

# FNN
class FNN(nn.Module):
    # 定义网络结构
    def __init__(self):
        super(FNN, self).__init__()
        self.layer1 = nn.Linear(28 * 28, 28)  # 隐藏层
        self.out = nn.Linear(28, 10)  # 输出层

    # 计算
    def forward(self, x):
        # 初始形状[batch_size, 1, 28, 28]
        x = x.view(-1, 28 * 28)
        x = torch.relu(self.layer1(x))  # 使用relu函数激活
        x = self.out(x)  # 输出层
        return x

结果：

3 CNN（卷积神经网络）

# CNN
class CNN(nn.Module):
    # 定义网络结构
    def __init__(self):
        super(CNN, self).__init__()
        # 卷积层+池化层+卷积层
        self.conv1 = nn.Conv2d(in_channels=1, out_channels=32, kernel_size=(3, 3), stride=(1, 1), padding=1)
        self.conv2 = nn.Conv2d(in_channels=32, out_channels=64, kernel_size=(3, 3), stride=(1, 1), padding=1)
        self.pool = nn.MaxPool2d(2, 2)
        # dropout
        self.dropout = nn.Dropout(p=0.25)
        # 全连接层
        self.fc1 = nn.Linear(64 * 7 * 7, 512)
        self.fc2 = nn.Linear(512, 64)
        self.fc3 = nn.Linear(64, 10)

    # 计算
    def forward(self, x):
        # 初始形状[batch_size, 1, 28, 28]
        x = self.pool(F.relu(self.conv1(x)))
        x = self.dropout(x)
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 64 * 7 * 7)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

结果：

4 RNN（循环神经网络）

# RNN
class RNN(nn.Module):
    # 定义网络结构
    def __init__(self):
        super(RNN, self).__init__()
        self.rnn = nn.RNN(input_size=28, hidden_size=64, num_layers=1, batch_first=True)  # RNN
        self.dropout = nn.Dropout(p=0.25)
        self.out = nn.Linear(64, 10)  # 全连接层

    # 计算
    def forward(self, x):
        x = x.view(-1, 28, 28)
        x = self.dropout(x)
        r_out, _ = self.rnn(x, None)
        x = self.out(r_out[:, -1, :])
        return x

结果：

5 LSTM（长短期记忆网络）

# LSTM
class LSTM(nn.Module):
    # 定义网络结构
    def __init__(self):
        super(LSTM, self).__init__()
        self.lstm = nn.LSTM(input_size=28, hidden_size=64, num_layers=1, batch_first=True)  # LSTM
        self.dropout = nn.Dropout(p=0.25)
        self.out = nn.Linear(64, 10)  # 全连接层

    # 计算
    def forward(self, x):
        x = x.view(-1, 28, 28)  # [64, 28, 28]
        x = self.dropout(x)
        r_out, _ = self.lstm(x, None)
        x = self.out(r_out[:, -1, :])  # [64, 10]
        return x

结果：

6 GRU（门控循环单元）

class GRU(nn.Module):
    # 定义网络结构
    def __init__(self):
        super(GRU, self).__init__()
        self.gru = nn.GRU(input_size=28, hidden_size=64, num_layers=1, batch_first=True)  # GRU
        self.dropout = nn.Dropout(p=0.25)
        self.out = nn.Linear(64, 10)  # 全连接层

    def forward(self, x):
        x = x.view(-1, 28, 28)
        x = self.dropout(x)
        r_out, _ = self.gru(x, None)
        x = self.out(r_out[:, -1, :])
        return x

结果：

7 完整代码

综合评价：物种模型均能达到96%以上的准确率。CNN效果最好，FNN其次，RNN、LSTM、GRU波动较大。

代码中封装了（造轮子）几个函数，包括get_accuracy()、train()、test()、run()、initialize()

"""
MNIST数据集分类
尝试使用FNN、CNN、RNN、LSTM、GRU
"""
import matplotlib.pyplot as plt
import torch
import time
import torch.nn.functional as F
from torch import nn, optim
from torchvision.datasets import MNIST
from torchvision.transforms import Compose, ToTensor, Normalize, Resize
from torch.utils.data import DataLoader
from sklearn.metrics import accuracy_score

# 超参数
BATCH_SIZE = 64  # 批次大小
EPOCHS = 5  # 迭代轮数
# 设备
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
# 数据转换
transformers = Compose(transforms=[ToTensor(), Normalize(mean=(0.1307,), std=(0.3081,))])
# 数据装载
dataset_train = MNIST(root=r'./data', train=True, download=False, transform=transformers)
dataset_test = MNIST(root=r'./data', train=False, download=False, transform=transformers)
dataloader_train = DataLoader(dataset=dataset_train, batch_size=BATCH_SIZE, shuffle=True)
dataloader_test = DataLoader(dataset=dataset_test, batch_size=BATCH_SIZE, shuffle=True)


# FNN
class FNN(nn.Module):
    # 定义网络结构
    def __init__(self):
        super(FNN, self).__init__()
        self.layer1 = nn.Linear(28 * 28, 28)  # 隐藏层
        self.out = nn.Linear(28, 10)  # 输出层

    # 计算
    def forward(self, x):
        # 初始形状[batch_size, 1, 28, 28]
        x = x.view(-1, 28 * 28)
        x = torch.relu(self.layer1(x))  # 使用relu函数激活
        x = self.out(x)  # 输出层
        return x


# CNN
class CNN(nn.Module):
    # 定义网络结构
    def __init__(self):
        super(CNN, self).__init__()
        # 卷积层+池化层+卷积层
        self.conv1 = nn.Conv2d(in_channels=1, out_channels=32, kernel_size=(3, 3), stride=(1, 1), padding=1)
        self.conv2 = nn.Conv2d(in_channels=32, out_channels=64, kernel_size=(3, 3), stride=(1, 1), padding=1)
        self.pool = nn.MaxPool2d(2, 2)
        # dropout
        self.dropout = nn.Dropout(p=0.25)
        # 全连接层
        self.fc1 = nn.Linear(64 * 7 * 7, 512)
        self.fc2 = nn.Linear(512, 64)
        self.fc3 = nn.Linear(64, 10)

    # 计算
    def forward(self, x):
        # 初始形状[batch_size, 1, 28, 28]
        x = self.pool(F.relu(self.conv1(x)))
        x = self.dropout(x)
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 64 * 7 * 7)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


# RNN
class RNN(nn.Module):
    # 定义网络结构
    def __init__(self):
        super(RNN, self).__init__()
        self.rnn = nn.RNN(input_size=28, hidden_size=64, num_layers=1, batch_first=True)  # RNN
        self.dropout = nn.Dropout(p=0.25)
        self.out = nn.Linear(64, 10)  # 全连接层

    # 计算
    def forward(self, x):
        x = x.view(-1, 28, 28)
        x = self.dropout(x)
        r_out, _ = self.rnn(x, None)
        x = self.out(r_out[:, -1, :])
        return x


# LSTM
class LSTM(nn.Module):
    # 定义网络结构
    def __init__(self):
        super(LSTM, self).__init__()
        self.lstm = nn.LSTM(input_size=28, hidden_size=64, num_layers=1, batch_first=True)  # LSTM
        self.dropout = nn.Dropout(p=0.25)
        self.out = nn.Linear(64, 10)  # 全连接层

    # 计算
    def forward(self, x):
        x = x.view(-1, 28, 28)  # [64, 28, 28]
        x = self.dropout(x)
        r_out, _ = self.lstm(x, None)
        x = self.out(r_out[:, -1, :])  # [64, 10]
        return x


class GRU(nn.Module):
    # 定义网络结构
    def __init__(self):
        super(GRU, self).__init__()
        self.gru = nn.GRU(input_size=28, hidden_size=64, num_layers=1, batch_first=True)  # GRU
        self.dropout = nn.Dropout(p=0.25)
        self.out = nn.Linear(64, 10)  # 全连接层

    def forward(self, x):
        x = x.view(-1, 28, 28)
        x = self.dropout(x)
        r_out, _ = self.gru(x, None)
        x = self.out(r_out[:, -1, :])
        return x


loss_func = nn.CrossEntropyLoss()  # 交叉熵损失函数
# 记录损失值、准确率
loss_list, accuracy_list = [], []


# 计算准确率
def get_accuracy(model, datas, labels):
    out = torch.softmax(model(datas), dim=1, dtype=torch.float32)
    predictions = torch.max(input=out, dim=1)[1]  # 最大值的索引
    y_predict = predictions.to('cpu').data.numpy()
    y_true = labels.to('cpu').data.numpy()
    # accuracy = float(np.sum(y_predict == y_true)) / float(y_true.size)  # 准确率
    accuracy = accuracy_score(y_true, y_predict)  # 准确率
    return accuracy


# 训练
def train(model, optimizer, epoch):
    model.train()  # 模型训练
    for i, (datas, labels) in enumerate(dataloader_train):
        # 设备转换
        datas = datas.to(DEVICE)
        labels = labels.to(DEVICE)
        # 计算结果
        out = model(datas)
        # 计算损失值
        loss = loss_func(out, labels)
        # 梯度清零
        optimizer.zero_grad()
        # 反向传播
        loss.backward()
        # 梯度更新
        optimizer.step()
        # 打印损失值
        if i % 100 == 0:
            print('Train Epoch:%d Loss:%0.6f' % (epoch, loss.item()))
            loss_list.append(loss.item())


# 测试
def test(model, epoch):
    model.eval()
    with torch.no_grad():
        for i, (datas, labels) in enumerate(dataloader_test):
            # 设备转换
            datas = datas.to(DEVICE)
            labels = labels.to(DEVICE)
            # 打印信息
            if i % 20 == 0:
                accuracy = get_accuracy(model, datas, labels)
                print('Test Epoch:%d Accuracy:%0.6f' % (epoch, accuracy))
                accuracy_list.append(accuracy)


# 运行
def run(model, optimizer, model_name):
    t1 = time.time()
    for epoch in range(EPOCHS):
        train(model, optimizer, epoch)
        test(model, epoch)
    t2 = time.time()
    print(f'共耗时{
      
      t2 - t1}秒')

    # 绘制Loss曲线
    plt.rcParams['figure.figsize'] = (16, 8)
    plt.subplots(1, 2)
    plt.subplot(1, 2, 1)
    plt.plot(range(len(loss_list)), loss_list)
    plt.title('Loss Curve')
    plt.subplot(1, 2, 2)
    plt.plot(range(len(accuracy_list)), accuracy_list)
    plt.title('Accuracy Cure')
    # plt.show()
    plt.savefig(f'./figure/mnist_{
      
      model_name}.png')


def initialize(model, model_name):
    print(f'Start {
      
      model_name}')
    # 查看分配显存
    print('GPU_Allocated:%d' % torch.cuda.memory_allocated())
    # 优化器
    optimizer = optim.Adam(params=model.parameters(), lr=0.001)
    run(model, optimizer, model_name)


if __name__ == '__main__':
    models = [FNN().to(DEVICE),
              CNN().to(DEVICE),
              LSTM().to(DEVICE),
              RNN().to(DEVICE),
              GRU().to(DEVICE)]
    model_names = ['FNN', 'CNN', 'RNN', 'LSTM', 'GRU']

    for model, model_name in zip(models, model_names):
        initialize(model, model_name)
        # 保存模型
        torch.save(model.state_dict(), f'./model/mnist_{
      
      model_name}.pkl')

欢迎点赞收藏关注。
本人深度学习小白一枚，如有误，欢迎留言指正。