pytorch 神經(jīng)網(wǎng)絡(luò)訓(xùn)練demo

數(shù)據(jù)集：MNIST

該數(shù)據(jù)集的內(nèi)容是手寫數(shù)字識(shí)別，其分為兩部分，分別含有60000張訓(xùn)練圖片和10000張測(cè)試圖片

神經(jīng)網(wǎng)絡(luò)：全連接網(wǎng)絡(luò)

# 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

# Create Fully Connected Network
class NN(nn.Module):
    def __init__(self, input_size, num_classes): #(28 * 28 = 784)
        super(NN, self).__init__()
        self.fc1 = nn.Linear(input_size, 50)
        self.fc2 = nn.Linear(50, num_classes)

    def forward(self, x):
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return x

model = NN(784, 10)
x = torch.randn(64, 784)

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

# Hyperparameters
input_size = 784
num_classes = 10
learning_rate = 0.001
batch_size = 64
num_epochs = 1


# 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)
# print(f'train_loader: {train_loader}')
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
model = NN(input_size=input_size, num_classes=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)
        targets = targets.to(device)
        # Get to correct shape
        # print(data.shape) # (batch_size, input_channel, height, width)
        data = data.reshape(data.shape[0], -1) # 64*784

        # forward
        scores = model(data) # 64*10
        # print(f'scores: {scores.shape}') # 64*10
        # print(f'targets: {targets.shape}') # 64*1
    
        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(): # 不計(jì)算梯度
        for x, y in loader:
            x = x.to(device)
            y = y.to(device)
            x = x.reshape(x.shape[0], -1) # 64*784

            scores = model(x)# 64*10
            # torch.max()這個(gè)函數(shù)返回的是兩個(gè)值：
                #第一個(gè)值是具體的value（我們用下劃線_表示）
                #第二個(gè)值是value所在的index（也就是predictions）。
            # 我們不關(guān)心最大值是什么，而關(guān)心最大值對(duì)應(yīng)的index是什么，所以選用下劃線代表不需要用到的變量。
            # 比如在圖像分類任務(wù)中，index就對(duì)應(yīng)著圖片的類別，這里我們只關(guān)心網(wǎng)絡(luò)預(yù)測(cè)的類別是什么，而不關(guān)心該類別的預(yù)測(cè)概率。
            _, predictions = scores.max(dim=1) #dim=1，表示對(duì)每行取最大值，每行代表一個(gè)樣本。
            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)

輸出結(jié)果

Checking accuracy on training data
Got 55770 / 60000 with accuracy 92.95%
Checking accuracy on test data
Got 9316 / 10000 with accuracy 93.16%

來源

【1】https://www.youtube.com/watch?v=Jy4wM2X21u0&list=PLhhyoLH6IjfxeoooqP9rhU3HJIAVAJ3Vz&index=3文章來源地址http://www.zghlxwxcb.cn/news/detail-579138.html

到了這里，關(guān)于PyTorch訓(xùn)練簡(jiǎn)單的全連接神經(jīng)網(wǎng)絡(luò)：手寫數(shù)字識(shí)別的文章就介紹完了。如果您還想了解更多內(nèi)容，請(qǐng)?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！