动手学深度学习PyTorch版——Task05学习笔记

卷积神经网络基础

import torch 
import torch.nn as nn

def corr2d(X, K):
    H, W = X.shape
    h, w = K.shape
    Y = torch.zeros(H - h + 1, W - w + 1)
    for i in range(Y.shape[0]):
        for j in range(Y.shape[1]):
            Y[i, j] = (X[i: i + h, j: j + w] * K).sum()
    return Y

X = torch.tensor([[0, 1, 2], [3, 4, 5], [6, 7, 8]])
K = torch.tensor([[0, 1], [2, 3]])
Y = corr2d(X, K)
print(Y)

二维卷积层

class Conv2D(nn.Module):
    def __init__(self, kernel_size):
        super(Conv2D, self).__init__()
        self.weight = nn.Parameter(torch.randn(kernel_size))
        self.bias = nn.Parameter(torch.randn(1))

    def forward(self, x):
        return corr2d(x, self.weight) + self.bias

例子，我们构造一张68的图像，中间4列为黑（0），其余为白（1），希望检测到颜色边缘。我们的标签是一个67的二维数组，第2列是1（从1到0的边缘），第6列是-1（从0到1的边缘）。

X = torch.ones(6, 8)
Y = torch.zeros(6, 7)
X[:, 2: 6] = 0
Y[:, 1] = 1
Y[:, 5] = -1
print(X)
print(Y)

我们希望学习一个卷积层，通过卷积层来检测颜色边缘。

conv2d = Conv2D(kernel_size=(1, 2))
step = 30
lr = 0.01
for i in range(step):
    Y_hat = conv2d(X)
    l = ((Y_hat - Y) ** 2).sum()
    l.backward()
    # 梯度下降
    conv2d.weight.data -= lr * conv2d.weight.grad
    conv2d.bias.data -= lr * conv2d.bias.grad
    
    # 梯度清零
    conv2d.weight.grad.zero_()
    conv2d.bias.grad.zero_()
    if (i + 1) % 5 == 0:
        print('Step %d, loss %.3f' % (i + 1, l.item()))
        
print(conv2d.weight.data)
print(conv2d.bias.data)

卷积层的简洁实现

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)

池化层的简洁实现

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)
print(X)
print(Y)

LeNet

#import
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): #将图像大小重定型
    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)
)

#print
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)

# 数据
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(
    batch_size=batch_size, root='/home/kesci/input/FashionMNIST2065')
print(len(train_iter))

获取数据和训练模型

#数据展示
import matplotlib.pyplot as plt
def show_fashion_mnist(images, labels):
    d2l.use_svg_display()
    # 这里的_表示我们忽略（不使用）的变量
    _, figs = plt.subplots(1, len(images), figsize=(12, 12))
    for f, img, lbl in zip(figs, images, labels):
        f.imshow(img.view((28, 28)).numpy())
        f.set_title(lbl)
        f.axes.get_xaxis().set_visible(False)
        f.axes.get_yaxis().set_visible(False)
    plt.show()

for Xdata,ylabel in train_iter:
    break
X, y = [], []
for i in range(10):
    print(Xdata[i].shape,ylabel[i].numpy())
    X.append(Xdata[i]) # 将第i个feature加到X中
    y.append(ylabel[i].numpy()) # 将第i个label加到y中
show_fashion_mnist(X, y)

# This function has been saved in the d2l package for future use
#use GPU
def try_gpu():
    """If GPU is available, return torch.device as cuda:0; else return torch.device as cpu."""
    if torch.cuda.is_available():
        device = torch.device('cuda:0')
    else:
        device = torch.device('cpu')
    return device

device = try_gpu()
device

#计算准确率
'''
(1). net.train()
  启用 BatchNormalization 和 Dropout，将BatchNormalization和Dropout置为True
(2). net.eval()
不启用 BatchNormalization 和 Dropout，将BatchNormalization和Dropout置为False
'''

def evaluate_accuracy(data_iter, net,device=torch.device('cpu')):
    """Evaluate accuracy of a model on the given data set."""
    acc_sum,n = torch.tensor([0],dtype=torch.float32,device=device),0
    for X,y in data_iter:
        # If device is the GPU, copy the data to the GPU.
        X,y = X.to(device),y.to(device)
        net.eval()
        with torch.no_grad():
            y = y.long()
            acc_sum += torch.sum((torch.argmax(net(X), dim=1) == y))  #[[0.2 ,0.4 ,0.5 ,0.6 ,0.8] ,[ 0.1,0.2 ,0.4 ,0.3 ,0.1]] => [ 4 , 2 ]
            n += y.shape[0]
    return acc_sum.item()/n

#训练函数
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))

# 训练
lr, num_epochs = 0.9, 10

def init_weights(m):
    if type(m) == nn.Linear or type(m) == nn.Conv2d:
        torch.nn.init.xavier_uniform_(m.weight)

net.apply(init_weights)
net = net.to(device)

criterion = nn.CrossEntropyLoss()   #交叉熵描述了两个概率分布之间的距离，交叉熵越小说明两者之间越接近
train_ch5(net, train_iter, test_iter, criterion,num_epochs, batch_size,device, lr)

# test
for testdata,testlabe in test_iter:
    testdata,testlabe = testdata.to(device),testlabe.to(device)
    break
print(testdata.shape,testlabe.shape)
net.eval()
y_pre = net(testdata)
print(torch.argmax(y_pre,dim=1)[:10])
print(testlabe[:10])

卷积神经网络进阶

深度卷积神经网络（AlexNet）

#目前GPU算力资源预计17日上线，在此之前本代码只能使用CPU运行。
#考虑到本代码中的模型过大，CPU训练较慢，
#我们还将代码上传了一份到 https://www.kaggle.com/boyuai/boyu-d2l-modernconvolutionalnetwork
#如希望提前使用gpu运行请至kaggle。


import time
import torch
from torch import nn, optim
import torchvision
import numpy as np
import sys
sys.path.append("/home/kesci/input/") 
import d2lzh1981 as d2l
import os
import torch.nn.functional as F

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

class AlexNet(nn.Module):
    def __init__(self):
        super(AlexNet, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(1, 96, 11, 4), # in_channels, out_channels, kernel_size, stride, padding
            nn.ReLU(),
            nn.MaxPool2d(3, 2), # kernel_size, stride
            # 减小卷积窗口，使用填充为2来使得输入与输出的高和宽一致，且增大输出通道数
            nn.Conv2d(96, 256, 5, 1, 2),
            nn.ReLU(),
            nn.MaxPool2d(3, 2),
            # 连续3个卷积层，且使用更小的卷积窗口。除了最后的卷积层外，进一步增大了输出通道数。
            # 前两个卷积层后不使用池化层来减小输入的高和宽
            nn.Conv2d(256, 384, 3, 1, 1),
            nn.ReLU(),
            nn.Conv2d(384, 384, 3, 1, 1),
            nn.ReLU(),
            nn.Conv2d(384, 256, 3, 1, 1),
            nn.ReLU(),
            nn.MaxPool2d(3, 2)
        )
         # 这里全连接层的输出个数比LeNet中的大数倍。使用丢弃层来缓解过拟合
        self.fc = nn.Sequential(
            nn.Linear(256*5*5, 4096),
            nn.ReLU(),
            nn.Dropout(0.5),
            #由于使用CPU镜像，精简网络，若为GPU镜像可添加该层
            #nn.Linear(4096, 4096),
            #nn.ReLU(),
            #nn.Dropout(0.5),

            # 输出层。由于这里使用Fashion-MNIST，所以用类别数为10，而非论文中的1000
            nn.Linear(4096, 10),
        )

    def forward(self, img):

        feature = self.conv(img)
        output = self.fc(feature.view(img.shape[0], -1))
        return output

net = AlexNet()
print(net)

载入数据集

# 本函数已保存在d2lzh_pytorch包中方便以后使用
def load_data_fashion_mnist(batch_size, resize=None, root='/home/kesci/input/FashionMNIST2065'):
    """Download the fashion mnist dataset and then load into memory."""
    trans = []
    if resize:
        trans.append(torchvision.transforms.Resize(size=resize))
    trans.append(torchvision.transforms.ToTensor())
    
    transform = torchvision.transforms.Compose(trans)
    mnist_train = torchvision.datasets.FashionMNIST(root=root, train=True, download=True, transform=transform)
    mnist_test = torchvision.datasets.FashionMNIST(root=root, train=False, download=True, transform=transform)

    train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=2)
    test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=2)

    return train_iter, test_iter

#batchsize=128
batch_size = 16
# 如出现“out of memory”的报错信息，可减小batch_size或resize
train_iter, test_iter = load_data_fashion_mnist(batch_size,224)
for X, Y in train_iter:
    print('X =', X.shape,
        '\nY =', Y.type(torch.int32))
    break

训练

lr, num_epochs = 0.001, 3
optimizer = torch.optim.Adam(net.parameters(), lr=lr)
d2l.train_ch5(net, train_iter, test_iter, batch_size, optimizer, device, num_epochs)

使用重复元素的网络（VGG）

VGG11的简单实现

def vgg_block(num_convs, in_channels, out_channels): #卷积层个数，输入通道数，输出通道数
    blk = []
    for i in range(num_convs):
        if i == 0:
            blk.append(nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1))
        else:
            blk.append(nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1))
        blk.append(nn.ReLU())
    blk.append(nn.MaxPool2d(kernel_size=2, stride=2)) # 这里会使宽高减半
    return nn.Sequential(*blk)

conv_arch = ((1, 1, 64), (1, 64, 128), (2, 128, 256), (2, 256, 512), (2, 512, 512))
# 经过5个vgg_block, 宽高会减半5次, 变成 224/32 = 7
fc_features = 512 * 7 * 7 # c * w * h
fc_hidden_units = 4096 # 任意

def vgg(conv_arch, fc_features, fc_hidden_units=4096):
    net = nn.Sequential()
    # 卷积层部分
    for i, (num_convs, in_channels, out_channels) in enumerate(conv_arch):
        # 每经过一个vgg_block都会使宽高减半
        net.add_module("vgg_block_" + str(i+1), vgg_block(num_convs, in_channels, out_channels))
    # 全连接层部分
    net.add_module("fc", nn.Sequential(d2l.FlattenLayer(),
                                 nn.Linear(fc_features, fc_hidden_units),
                                 nn.ReLU(),
                                 nn.Dropout(0.5),
                                 nn.Linear(fc_hidden_units, fc_hidden_units),
                                 nn.ReLU(),
                                 nn.Dropout(0.5),
                                 nn.Linear(fc_hidden_units, 10)
                                ))
    return net

net = vgg(conv_arch, fc_features, fc_hidden_units)
X = torch.rand(1, 1, 224, 224)

# named_children获取一级子模块及其名字(named_modules会返回所有子模块,包括子模块的子模块)
for name, blk in net.named_children(): 
    X = blk(X)
    print(name, 'output shape: ', X.shape)

ratio = 8
small_conv_arch = [(1, 1, 64//ratio), (1, 64//ratio, 128//ratio), (2, 128//ratio, 256//ratio), 
                   (2, 256//ratio, 512//ratio), (2, 512//ratio, 512//ratio)]
net = vgg(small_conv_arch, fc_features // ratio, fc_hidden_units // ratio)
print(net)

batchsize=16
#batch_size = 64
# 如出现“out of memory”的报错信息，可减小batch_size或resize
# train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)

lr, num_epochs = 0.001, 5
optimizer = torch.optim.Adam(net.parameters(), lr=lr)
d2l.train_ch5(net, train_iter, test_iter, batch_size, optimizer, device, num_epochs)

网络中的网络（NiN）

def nin_block(in_channels, out_channels, kernel_size, stride, padding):
    blk = nn.Sequential(nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding),
                        nn.ReLU(),
                        nn.Conv2d(out_channels, out_channels, kernel_size=1),
                        nn.ReLU(),
                        nn.Conv2d(out_channels, out_channels, kernel_size=1),
                        nn.ReLU())
    return blk

# 已保存在d2lzh_pytorch
class GlobalAvgPool2d(nn.Module):
    # 全局平均池化层可通过将池化窗口形状设置成输入的高和宽实现
    def __init__(self):
        super(GlobalAvgPool2d, self).__init__()
    def forward(self, x):
        return F.avg_pool2d(x, kernel_size=x.size()[2:])

net = nn.Sequential(
    nin_block(1, 96, kernel_size=11, stride=4, padding=0),
    nn.MaxPool2d(kernel_size=3, stride=2),
    nin_block(96, 256, kernel_size=5, stride=1, padding=2),
    nn.MaxPool2d(kernel_size=3, stride=2),
    nin_block(256, 384, kernel_size=3, stride=1, padding=1),
    nn.MaxPool2d(kernel_size=3, stride=2), 
    nn.Dropout(0.5),
    # 标签类别数是10
    nin_block(384, 10, kernel_size=3, stride=1, padding=1),
    GlobalAvgPool2d(), 
    # 将四维的输出转成二维的输出，其形状为(批量大小, 10)
    d2l.FlattenLayer())

X = torch.rand(1, 1, 224, 224)
for name, blk in net.named_children(): 
    X = blk(X)
    print(name, 'output shape: ', X.shape)

batch_size = 128
# 如出现“out of memory”的报错信息，可减小batch_size或resize
#train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)

lr, num_epochs = 0.002, 5
optimizer = torch.optim.Adam(net.parameters(), lr=lr)
d2l.train_ch5(net, train_iter, test_iter, batch_size, optimizer, device, num_epochs)

GoogLeNet

class Inception(nn.Module):
    # c1 - c4为每条线路里的层的输出通道数
    def __init__(self, in_c, c1, c2, c3, c4):
        super(Inception, self).__init__()
        # 线路1，单1 x 1卷积层
        self.p1_1 = nn.Conv2d(in_c, c1, kernel_size=1)
        # 线路2，1 x 1卷积层后接3 x 3卷积层
        self.p2_1 = nn.Conv2d(in_c, c2[0], kernel_size=1)
        self.p2_2 = nn.Conv2d(c2[0], c2[1], kernel_size=3, padding=1)
        # 线路3，1 x 1卷积层后接5 x 5卷积层
        self.p3_1 = nn.Conv2d(in_c, c3[0], kernel_size=1)
        self.p3_2 = nn.Conv2d(c3[0], c3[1], kernel_size=5, padding=2)
        # 线路4，3 x 3最大池化层后接1 x 1卷积层
        self.p4_1 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
        self.p4_2 = nn.Conv2d(in_c, c4, kernel_size=1)

    def forward(self, x):
        p1 = F.relu(self.p1_1(x))
        p2 = F.relu(self.p2_2(F.relu(self.p2_1(x))))
        p3 = F.relu(self.p3_2(F.relu(self.p3_1(x))))
        p4 = F.relu(self.p4_2(self.p4_1(x)))
        return torch.cat((p1, p2, p3, p4), dim=1)  # 在通道维上连结输出

GoogLeNet模型

b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
                   nn.ReLU(),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

b2 = nn.Sequential(nn.Conv2d(64, 64, kernel_size=1),
                   nn.Conv2d(64, 192, kernel_size=3, padding=1),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

b3 = nn.Sequential(Inception(192, 64, (96, 128), (16, 32), 32),
                   Inception(256, 128, (128, 192), (32, 96), 64),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

b4 = nn.Sequential(Inception(480, 192, (96, 208), (16, 48), 64),
                   Inception(512, 160, (112, 224), (24, 64), 64),
                   Inception(512, 128, (128, 256), (24, 64), 64),
                   Inception(512, 112, (144, 288), (32, 64), 64),
                   Inception(528, 256, (160, 320), (32, 128), 128),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

b5 = nn.Sequential(Inception(832, 256, (160, 320), (32, 128), 128),
                   Inception(832, 384, (192, 384), (48, 128), 128),
                   d2l.GlobalAvgPool2d())

net = nn.Sequential(b1, b2, b3, b4, b5, 
                    d2l.FlattenLayer(), nn.Linear(1024, 10))

net = nn.Sequential(b1, b2, b3, b4, b5, d2l.FlattenLayer(), nn.Linear(1024, 10))

X = torch.rand(1, 1, 96, 96)

for blk in net.children(): 
    X = blk(X)
    print('output shape: ', X.shape)

#batchsize=128
batch_size = 16
# 如出现“out of memory”的报错信息，可减小batch_size或resize
#train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=96)

lr, num_epochs = 0.001, 5
optimizer = torch.optim.Adam(net.parameters(), lr=lr)
d2l.train_ch5(net, train_iter, test_iter, batch_size, optimizer, device, num_epochs)