pytorch手寫實作數字辨識

知識點補充

• view()

• 在PyTorch中view函式作用為重構張量的維度，相當于numpy中的resize()的功能

• torch.nn.CrossEntropyLoss()

• 求交叉熵，并且其中嵌套了log 和softmax 函式 所以i神經網路最后一層不用再用softmax激活

• torch.max(input, dim)

輸入

• input是softmax函式輸出的一個tensor
• dim是max函式索引的維度0/1，0是每列的最大值，1是每行的最大值

輸出

• 函式會回傳兩個tensor，第一個tensor是每行的最大值；第二個tensor是每行最大值的索引，

1、準備資料集

transform = transforms.Compose([    #撰寫轉換器
    transforms.ToTensor(), #資料轉為向量
    transforms.Normalize((0.1307,), (0.3801, )) #將像素值規格化在(0, 1)之間，前者為均值，后者為方差，這兩個值是在影像處理上經過大量資料得到的普遍值
])

train_dataset = datasets.MNIST(
    root = '../dataset/minist',
    train = True,
    download = True,
    transform = transform
)

train_loader = DataLoader(train_dataset,
                          shuffle=True, #訓練資料打亂保證隨機性
                          batch_size=64)

test_dataset = datasets.MNIST(
    root = '../dataset/minist',
    train = False,
    download = True,
    transform = transform
)

test_loader = DataLoader(train_dataset,
                          shuffle=False,    #測驗集不打算保證結果直觀性
                          batch_size=64)

2、構建神經網路

class Net(torch.nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        self.l1 = torch.nn.Linear(784, 512)
        self.l2 = torch.nn.Linear(512, 256)
        self.l3 = torch.nn.Linear(256, 128)
        self.l4 = torch.nn.Linear(128, 64)
        self.l5 = torch.nn.Linear(64, 10)

    def forward(self, x):
        x = x.view(-1, 784)     #將x轉為N*784的向量
        x = F.relu(self.l1(x))
        x = F.relu(self.l2(x))
        x = F.relu(self.l3(x))
        x = F.relu(self.l4(x))

        return self.l5(x)       #最后一層不做softmax，因為等會呼叫的交叉熵函式包含了softmax的程序


model = Net()

3、定義loss和optimizer

criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5) #momentum:相當于賦予梯度慣性幫助跳出local minimal

4、訓練

def train(epoch):
    runing_loss = 0.0
    for batch_idx, data in enumerate(train_loader,0):
        inputs, target = data
        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()
        runing_loss += loss.item()

        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx +1, runing_loss / 300))
            runing_loss = 0.0

5、測驗

def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            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))

完整代碼

import torch
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

# 1、準備資料集

transform = transforms.Compose([    #撰寫轉換器
    transforms.ToTensor(), #資料轉為向量
    transforms.Normalize((0.1307,), (0.3801, )) #將像素值規格化在(0, 1)之間，前者為均值，后者為方差，這兩個值是在影像處理上經過大量資料得到的普遍值
])

train_dataset = datasets.MNIST(
    root = '../dataset/minist',
    train = True,
    download = True,
    transform = transform
)

train_loader = DataLoader(train_dataset,
                          shuffle=True, #訓練資料打亂保證隨機性
                          batch_size=64)

test_dataset = datasets.MNIST(
    root = '../dataset/minist',
    train = False,
    download = True,
    transform = transform
)

test_loader = DataLoader(train_dataset,
                          shuffle=False,    #測驗集不打算保證結果直觀性
                          batch_size=64)

# 2、構建神經網路

class Net(torch.nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        self.l1 = torch.nn.Linear(784, 512)
        self.l2 = torch.nn.Linear(512, 256)
        self.l3 = torch.nn.Linear(256, 128)
        self.l4 = torch.nn.Linear(128, 64)
        self.l5 = torch.nn.Linear(64, 10)

    def forward(self, x):
        x = x.view(-1, 784)     #將x轉為N*784的向量
        x = F.relu(self.l1(x))
        x = F.relu(self.l2(x))
        x = F.relu(self.l3(x))
        x = F.relu(self.l4(x))

        return self.l5(x)       #最后一層不做softmax，因為等會呼叫的交叉熵函式包含了softmax的程序


model = Net()

# 3、定義loss和optimizer

criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5) #momentum:相當于賦予梯度慣性幫助跳出local minimal



# 4、訓練

def train(epoch):
    runing_loss = 0.0
    for batch_idx, data in enumerate(train_loader,0):
        inputs, target = data
        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()
        runing_loss += loss.item()

        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx +1, runing_loss / 300))
            runing_loss = 0.0

# 5、測驗

def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            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))


if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()