pytorch學習－－卷積神經網絡

代碼源自：https://github.com/yunjey/pytorch-tutorial
這裏只是將其做爲一個學習樣例．

＃引入包
import torch 
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms

                
# Device configuration　有顯卡默認加載cuda0，否則用cpu
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

# Hyper parameters
num_epochs = 5
num_classes = 10 #分類數目
batch_size = 100 
learning_rate = 0.001#學習率

# MNIST dataset
train_dataset = torchvision.datasets.MNIST(root='../../data/',
                                           train=True, 
                                           transform=transforms.ToTensor(),
                                           download=True)

test_dataset = torchvision.datasets.MNIST(root='../../data/',
                                          train=False, 
                                          transform=transforms.ToTensor())

# Data loader
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size, 
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size, 
                                          shuffle=False)

# Convolutional neural network (two convolutional layers)
#各個層的輸入輸出計算
#conv層　out = {(input_height - kernel_size + 2*padding) / stride[0] }+1 
#pooling   out ={ (input_height - kernel_size)/stride[0]} + 1

#Sequential就是個容器，把各個層放在一起組成一個大層
＃BatchNorm2d　BN層對於每個隱層神經元，把逐漸向非線性函數映射後向取值區間極限飽和區靠攏的輸入分佈強制
＃拉回到均值爲0方差爲1的比較標準的正態分佈，使得非線性變換函數的輸入值落入對輸入比較敏感的區域，以此避免
＃梯度消失問題。
＃ReLU　激活層，非線性
＃MaxPool2d　層，　1. invariance(不變性)，這種不變性包括translation(平移)，rotation(旋轉)，scale(尺度)
＃　2. 保留主要的特徵同時減少參數(降維，效果類似PCA)和計算量，防止過擬合，提高模型泛化能力
class ConvNet(nn.Module):
    def __init__(self, num_classes=10):
        super(ConvNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2), # (28 - 5 + 2*2)/1 + 1 =  28
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)) #(28 - 2)/2 + 1 = 14
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),#(14 - 5 +4)/1 + 1 = 14
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2)) #(14 - 2)/2 + 1 = 7
        self.fc = nn.Linear(7*7*32, num_classes)
        
    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(), -1)
        out = self.fc(out)
        return out

model = ConvNet(num_classes).to(device)

# Loss and optimizer 損失與優化器定義
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# Train the model
total_step = len(train_loader)＃每個epoch訓練的次數
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)
        
        # Forward pass　前向傳播
        outputs = model(images)
        loss = criterion(outputs, labels)
        
        # Backward and optimize　反向傳播及優化
        optimizer.zero_grad()#優化器每一次要先置０
        loss.backward()
        optimizer.step()
        
        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# Test the model
model.eval()  # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)＃例子中是(100,10)#這種輸出結果， torch.max兩個輸出，最大值與
                                                                         #index,而我們只關心索引，做爲結果輸出，每一行的最大值
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))

# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')

基本流程：

１．下載並加載數據
２．定義網絡
３．定義loss及優化器
４．定義訓練各種參數
５．訓練
６．測試集上測試
７．保存模型

[參考文檔]
https://www.cnblogs.com/guoyaohua/p/8724433.html
https://blog.csdn.net/zxyhhjs2017/article/details/78607469