Task05:卷積神經網絡基礎+LeNet

卷積神經網絡

感受野

LeNet架構

卷積層

互相關運算與卷積運算
卷積層得名於卷積運算，但卷積層中用到的並非卷積運算而是互相關運算。我們將核數組上下翻轉、左右翻轉，再與輸入數組做互相關運算，這一過程就是卷積運算。由於卷積層的核數組是可學習的，所以使用互相關運算與使用卷積運算並無本質區別。

填充

步幅

多輸入通道和多輸出通道

卷積層的簡潔實現

X = torch.rand(4, 2, 3, 5)
print(X.shape)

conv2d = nn.Conv2d(in_channels=2, out_channels=3, kernel_size=(3, 5), stride=1, padding=(1, 2))
Y = conv2d(X)
print('Y.shape: ', Y.shape)
print('weight.shape: ', conv2d.weight.shape)
print('bias.shape: ', conv2d.bias.shape)

池化層

在區域裏進行降採樣

X = torch.arange(32, dtype=torch.float32).view(1, 2, 4, 4)
pool2d = nn.MaxPool2d(kernel_size=3, padding=1, stride=(2, 1))
Y = pool2d(X)
# 平均池化層使用的是nn.AvgPool2d，使用方法與nn.MaxPool2d相同。

#下面我們通過Sequential類來實現LeNet模型。
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l
import torch
import torch.nn as nn
import torch.optim as optim
import time
#net
class Flatten(torch.nn.Module):  #展平操作
    def forward(self, x):
        return x.view(x.shape[0], -1)

class Reshape(torch.nn.Module): #將圖像大小重定型
    def forward(self, x):
        return x.view(-1,1,28,28)      #(B x C x H x W)
    
net = torch.nn.Sequential(     #Lelet                                                  
    Reshape(),
    nn.Conv2d(in_channels=1, out_channels=6, kernel_size=5, padding=2), #b*1*28*28  =>b*6*28*28
    nn.Sigmoid(),                                                       
    nn.AvgPool2d(kernel_size=2, stride=2),                              #b*6*28*28  =>b*6*14*14
    nn.Conv2d(in_channels=6, out_channels=16, kernel_size=5),           #b*6*14*14  =>b*16*10*10
    nn.Sigmoid(),
    nn.AvgPool2d(kernel_size=2, stride=2),                              #b*16*10*10  => b*16*5*5
    Flatten(),                                                          #b*16*5*5   => b*400
    nn.Linear(in_features=16*5*5, out_features=120),
    nn.Sigmoid(),
    nn.Linear(120, 84),
    nn.Sigmoid(),
    nn.Linear(84, 10)
)
#接下來我們構造一個高和寬均爲28的單通道數據樣本，並逐層進行前向計算來查看每個層的輸出形狀。
X = torch.randn(size=(1,1,28,28), dtype = torch.float32)
for layer in net:
    X = layer(X)
    print(layer.__class__.__name__,'output shape: \t',X.shape)

可以看到，在卷積層塊中輸入的高和寬在逐層減小。卷積層由於使用高和寬均爲5的卷積核，從而將高和寬分別減小4，而池化層則將高和寬減半，但通道數則從1增加到16。全連接層則逐層減少輸出個數，直到變成圖像的類別數10。

#訓練函數
def train_ch5(net, train_iter, test_iter,criterion, num_epochs, batch_size, device,lr=None):
    """Train and evaluate a model with CPU or GPU."""
    print('training on', device)
    net.to(device)
    optimizer = optim.SGD(net.parameters(), lr=lr)
    for epoch in range(num_epochs):
        train_l_sum = torch.tensor([0.0],dtype=torch.float32,device=device)
        train_acc_sum = torch.tensor([0.0],dtype=torch.float32,device=device)
        n, start = 0, time.time()
        for X, y in train_iter:
            net.train()
            
            optimizer.zero_grad()
            X,y = X.to(device),y.to(device) 
            y_hat = net(X)
            loss = criterion(y_hat, y)
            loss.backward()
            optimizer.step()
            
            with torch.no_grad():
                y = y.long()
                train_l_sum += loss.float()
                train_acc_sum += (torch.sum((torch.argmax(y_hat, dim=1) == y))).float()
                n += y.shape[0]
        test_acc = evaluate_accuracy(test_iter, net,device)
        print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f, '
              'time %.1f sec'
              % (epoch + 1, train_l_sum/n, train_acc_sum/n, test_acc,
                 time.time() - start))