PyTorch训练RNN, GRU, LSTM:手写数字识别

文章目录

pytorch 神经网络训练demo

数据集:MNIST

该数据集的内容是手写数字识别,其分为两部分,分别含有60000张训练图片和10000张测试图片

图片来源:https://tensornews.cn/mnist_intro/

神经网络:RNN, GRU, LSTM

python 复制代码
# Imports
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.utils.data import DataLoader
import torchvision.datasets as datasets
import torchvision.transforms as transforms

# Set device
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# Hyperparameters
input_size = 28
sequence_length = 28
num_layers = 2
hidden_size = 256
num_classes = 10
learning_rate = 0.001
batch_size = 64
num_epochs = 2

# Create a RNN
class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(RNN, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.rnn = nn.RNN(input_size, hidden_size, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_size*sequence_length, num_classes) # fully connected
    
    def forward(self, x):
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)

        # Forward Prop
        out, _ = self.rnn(x, h0)
        out = out.reshape(out.shape[0], -1)
        out = self.fc(out)

        return out
    
# Create a GRU
class RNN_GRU(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(RNN_GRU, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.gru = nn.GRU(input_size, hidden_size, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_size*sequence_length, num_classes) # fully connected
    
    def forward(self, x):
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)

        # Forward Prop
        out, _ = self.gru(x, h0)
        out = out.reshape(out.shape[0], -1)
        out = self.fc(out)

        return out


# Create a LSTM
class RNN_LSTM(nn.Module):
    def __init__(self, input_size, hidden_size, num_layers, num_classes):
        super(RNN_LSTM, self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.lstm = nn.LSTM(input_size, hidden_size, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_size*sequence_length, num_classes) # fully connected
    
    def forward(self, x):
        h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)
        c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size).to(device)

        # Forward Prop
        out, _ = self.lstm(x, (h0, c0))
        out = out.reshape(out.shape[0], -1)
        out = self.fc(out)
        return out
    

# Load data
train_dataset = datasets.MNIST(root='dataset/', 
                               train=True, 
                               transform=transforms.ToTensor(),
                               download=True)
train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
test_dataset = datasets.MNIST(root='dataset/', 
                              train=False, 
                               transform=transforms.ToTensor(),
                               download=True)
test_loader = DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=True)

# Initialize network 选择一个即可
model = RNN(input_size, hidden_size, num_layers, num_classes).to(device)
# model = RNN_GRU(input_size, hidden_size, num_layers, num_classes).to(device)
# model = RNN_LSTM(input_size, hidden_size, num_layers, num_classes).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)

# Train network
for epoch in range(num_epochs):
    # data: images, targets: labels
    for batch_idx, (data, targets) in enumerate(train_loader):
        # Get data to cuda if possible
        data = data.to(device).squeeze(1) # 删除一个张量中所有维数为1的维度 (N, 1, 28, 28) -> (N, 28, 28)
        targets = targets.to(device)

        # forward
        scores = model(data) # 64*10
        loss = criterion(scores, targets)

        # backward
        optimizer.zero_grad()
        loss.backward()

        # gradient descent or adam step
        optimizer.step()


# Check accuracy on training & test to see how good our model
def check_accuracy(loader, model):
    if loader.dataset.train:
        print("Checking accuracy on training data")
    else:
        print("Checking accuracy on test data")
    num_correct = 0
    num_samples = 0
    model.eval()

    with torch.no_grad(): # 不计算梯度
        for x, y in loader:
            x = x.to(device).squeeze(1)
            y = y.to(device)
            # x = x.reshape(x.shape[0], -1) # 64*784

            scores = model(x)# 64*10
            _, predictions = scores.max(dim=1) #dim=1,表示对每行取最大值,每行代表一个样本。
            num_correct += (predictions == y).sum()
            num_samples += predictions.size(0) # 64

        print(f'Got {num_correct} / {num_samples} with accuracy {float(num_correct)/float(num_samples)*100:.2f}%')

    model.train()

check_accuracy(train_loader, model)
check_accuracy(test_loader, model)

Result

python 复制代码
RNN Result
Checking accuracy on training data
Got 57926 / 60000 with accuracy 96.54%
Checking accuracy on test data
Got 9640 / 10000 with accuracy 96.40%


GRU Result
Checking accuracy on training data
Got 59058 / 60000 with accuracy 98.43%
Checking accuracy on test data
Got 9841 / 10000 with accuracy 98.41%

LSTM Result
Checking accuracy on training data
Got 59248 / 60000 with accuracy 98.75%
Checking accuracy on test data
Got 9849 / 10000 with accuracy 98.49%

参考来源

【1】https://www.youtube.com/watch?v=Gl2WXLIMvKA\&list=PLhhyoLH6IjfxeoooqP9rhU3HJIAVAJ3Vz\&index=5

相关推荐
意念回复2 天前
从 RNN 到 GQA:自注意力与多头注意力机制全解析
人工智能·rnn·深度学习
Be for thing5 天前
Pytorch【12】transforms进阶|图像数据增强实战,提升模型泛化能力
人工智能·pytorch·机器学习
电科_银尘7 天前
【深度学习项目实战·33】自定义数据集:把自己的图片接入PyTorch
人工智能·pytorch·深度学习
aifannihao8 天前
AI 学习第 14 课:CNN 训 6 轮卡在 0.5352,数据没打乱
pytorch·python·深度学习·cnn·学习路线
2601_967987379 天前
Scikit-Learn 1.8引入Array,支持 PyTorch 与 CuPy 张量的原生 GPU 加速
pytorch·scikit-learn·交叉验证·gpu加速·cupy
盼小辉丶9 天前
PyTorch强化学习实战(35)——多智能体强化学习
人工智能·pytorch·深度学习·强化学习
SJZR10 天前
图解循环神经网络(RNN)
人工智能·rnn·神经网络
一条大祥脚11 天前
深入理解 PyTorch FlexAttention:从 Score Mod 到 Mask Mod 的稀疏加速之道
人工智能·pytorch·python·注意力机制·flex attention·可编程注意力
Yolanda_202211 天前
week4(下)
pytorch