pytorch自学笔记——LeNet+AlexNet+VGG+NiN+GoogleNet

一、LeNet

 LeNet（LeNet-5）由两个部分组成： * 卷积编码器：由两个卷积层组成; * 全连接层密集块：由三个全连接层组成。

卷积块 = 卷积层 + 激活函数 + 池化层

import torch
from torch import nn
from d2l import torch as d2l

class Reshape(torch.nn.Module):
    def forward(self, x):
        #view见函数解读
        #-1代表的是批量数不变，1代表的是通道数，（28，28）代表的是图片的size
        #(-1, 1, 28, 28)也代表了pytorch输入数据的格式必学是一个4维的tensor
        return x.view(-1, 1, 28, 28)

#nn.Conv2d(1, 6, kernel_size=5,padding=2)，其中的1对应的是通道数，输通道是6
#也可以说卷积核的个数是6，每个卷积核的大小是5*5

#nn.Conv2d(6, 16, kernel_size=5)
#同理卷积核的个数是16，大小是5*5

#nn.Linear(16 * 5 * 5, 120)
#这里是pytorch做的不好的地方，不能自己去设置16 * 5 * 5这个参数
#解决办法见下面的for layer in net:
#将每层的大小全部输出出来然后你可以自己填进去
#核心还是要自己会计算大小，具体计算公式见onenote吴恩达

net = torch.nn.Sequential(Reshape(), nn.Conv2d(1, 6, kernel_size=5,
                                               padding=2), nn.Sigmoid(),
                          nn.AvgPool2d(kernel_size=2, stride=2),
                          nn.Conv2d(6, 16, kernel_size=5), nn.Sigmoid(),
                          nn.AvgPool2d(kernel_size=2, stride=2), nn.Flatten(),
                          nn.Linear(16 * 5 * 5, 120), nn.Sigmoid(),
                          nn.Linear(120, 84), nn.Sigmoid(), nn.Linear(84, 10))


X = torch.rand(size=(1, 1, 28, 28), dtype=torch.float32)
for layer in net:
    X = layer(X)
    print(layer.__class__.__name__, 'output shape: \t', X.shape)

#读取训练集和测试集
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size=batch_size)


def evaluate_accuracy_gpu(net, data_iter, device=None):  #@save
    """使用GPU计算模型在数据集上的精度。"""
    if isinstance(net, torch.nn.Module):
        net.eval()  # 设置为评估模式
        if not device:
            device = next(iter(net.parameters())).device
    # 正确预测的数量，总预测的数量
    metric = d2l.Accumulator(2)
    for X, y in data_iter:
        if isinstance(X, list):
            # BERT微调所需的（之后将介绍）
            X = [x.to(device) for x in X]
        else:
            X = X.to(device)
        y = y.to(device)
        metric.add(d2l.accuracy(net(X), y), y.numel())
    return metric[0] / metric[1]

#@save
def train_ch6(net, train_iter, test_iter, num_epochs, lr, device):
    """用GPU训练模型(在第六章定义)。"""
    def init_weights(m):
        if type(m) == nn.Linear or type(m) == nn.Conv2d:
            nn.init.xavier_uniform_(m.weight)

    net.apply(init_weights)
    print('training on', device)
    net.to(device)
    optimizer = torch.optim.SGD(net.parameters(), lr=lr)
    loss = nn.CrossEntropyLoss()
    animator = d2l.Animator(xlabel='epoch', xlim=[1, num_epochs],
                            legend=['train loss', 'train acc', 'test acc'])
    timer, num_batches = d2l.Timer(), len(train_iter)
    for epoch in range(num_epochs):
        # 训练损失之和，训练准确率之和，范例数
        metric = d2l.Accumulator(3)
        net.train()
        for i, (X, y) in enumerate(train_iter):
            timer.start()
            optimizer.zero_grad()
            X, y = X.to(device), y.to(device)
            y_hat = net(X)
            l = loss(y_hat, y)
            l.backward()
            optimizer.step()
            with torch.no_grad():
                metric.add(l * X.shape[0], d2l.accuracy(y_hat, y), X.shape[0])
            timer.stop()
            train_l = metric[0] / metric[2]
            train_acc = metric[1] / metric[2]
            if (i + 1) % (num_batches // 5) == 0 or i == num_batches - 1:
                animator.add(epoch + (i + 1) / num_batches,
                             (train_l, train_acc, None))
        test_acc = evaluate_accuracy_gpu(net, test_iter)
        animator.add(epoch + 1, (None, None, test_acc))
    print(f'loss {train_l:.3f}, train acc {train_acc:.3f}, '
          f'test acc {test_acc:.3f}')
    print(f'{metric[2] * num_epochs / timer.sum():.1f} examples/sec '
          f'on {str(device)}')

lr, num_epochs = 0.9, 10
train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())

函数解析：

1、view函数

view函数相当于numpy中的reshape，它就是对一个tensor进行变形

二、AletxNet

image.size = 1*224*224

import torch
from torch import nn
from d2l import torch as d2l

net = nn.Sequential(
    nn.Conv2d(1, 96, kernel_size=11, stride=4, padding=1), nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),
    nn.Conv2d(96, 256, kernel_size=5, padding=2), nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),
    nn.Conv2d(256, 384, kernel_size=3, padding=1), nn.ReLU(),
    nn.Conv2d(384, 384, kernel_size=3, padding=1), nn.ReLU(),
    nn.Conv2d(384, 256, kernel_size=3, padding=1), nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2), nn.Flatten(),
    nn.Linear(6400, 4096), nn.ReLU(), nn.Dropout(p=0.5),
    nn.Linear(4096, 4096), nn.ReLU(), nn.Dropout(p=0.5),
    nn.Linear(4096, 10))

X = torch.randn(1, 1, 224, 224)
for layer in net:
    X = layer(X)
    print(layer.__class__.__name__, 'Output shape:\t', X.shape)

batch_size = 128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)

lr, num_epochs = 0.01, 10
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())

三、VGG

import torch
from torch import nn
from d2l import torch as d2l


#定义vgg块——以后vgg块全部可以按照这个格式来定义

#num_convs：卷积层的层数
#in_channels：输入通道数
#out_channels输出通道数——卷积核的个数

def vgg_block(num_convs, in_channels, out_channels):
    layers = []
    for _ in range(num_convs):
        layers.append(
            nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1))
        layers.append(nn.ReLU())
        in_channels = out_channels
    layers.append(nn.MaxPool2d(kernel_size=2, stride=2))
    return nn.Sequential(*layers)

#这里一共用了5个vgg块。why？
#224只能出5个2————上面的池化层会将每张特征图的长宽缩减为原来的一半（nn.MaxPool2d(kernel_size=2, stride=2)）

#：1+1+2+2+2=卷积层的个数
#：64，128，256，256，512，512，512，512分别代表每个卷积层中卷积核的个数
conv_arch = ((1, 64), (1, 128), (2, 256), (2, 512), (2, 512))

def vgg(conv_arch):
    conv_blks = []
    in_channels = 1
    for (num_convs, out_channels) in conv_arch:
        conv_blks.append(vgg_block(num_convs, in_channels, out_channels))
        in_channels = out_channels

    return nn.Sequential(*conv_blks, nn.Flatten(),
                         nn.Linear(out_channels * 7 * 7, 4096), nn.ReLU(),
                         nn.Dropout(0.5), nn.Linear(4096, 4096), nn.ReLU(),
                         nn.Dropout(0.5), nn.Linear(4096, 10))

net = vgg(conv_arch)

X = torch.randn(size=(1, 1, 224, 224))
for blk in net:
    X = blk(X)
    print(blk.__class__.__name__, 'output shape:\t', X.shape)

ratio = 4
small_conv_arch = [(pair[0], pair[1] // ratio) for pair in conv_arch]
net = vgg(small_conv_arch)

lr, num_epochs, batch_size = 0.05, 10, 128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())

感觉vgg也没做什么，我们不断的往nn.Sequential()手动加入卷积层也可达到同样的目的。vgg就在于将这个手动加卷积层的过程简化了，使得模型变深变得更加方便。

四、NiN

核心思想：全全连接层是对每个像素都加不同的权重——这样会使得参数过多，出现过拟合的问题。而NiN用卷积层对每个通道都加一个相同的参数——所有像素加相同的参数。

import torch
from torch import nn
from d2l import torch as d2l

def nin_block(in_channels, out_channels, kernel_size, strides, padding):
    return nn.Sequential(
        nn.Conv2d(in_channels, out_channels, kernel_size, strides, 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())
#相当于对一个矩阵中所有元素都乘了同一个数字（权重）——对一个图片都用一个权重

#图片缩小的核心在于池化层——nn.MaxPool2d(3, stride=2),stride=2高宽减半
net = nn.Sequential(
    nin_block(1, 96, kernel_size=11, strides=4, padding=0),
    nn.MaxPool2d(3, stride=2),
    nin_block(96, 256, kernel_size=5, strides=1, padding=2),
    nn.MaxPool2d(3, stride=2),
    nin_block(256, 384, kernel_size=3, strides=1, padding=1),
    nn.MaxPool2d(3, stride=2), nn.Dropout(0.5),
    #将通道数降为10——10要用来做分类的
    nin_block(384, 10, kernel_size=3, strides=1, padding=1),       
    #全局的平均池化层——使得10个通道都变成高宽为1的标量
    nn.AdaptiveAvgPool2d((1, 1)),                                  
    nn.Flatten())


X = torch.rand(size=(1, 1, 224, 224))
for layer in net:
    X = layer(X)
    print(layer.__class__.__name__, 'output shape:\t', X.shape)


lr, num_epochs, batch_size = 0.1, 10, 128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())

五、GoogleNet

import torch
from torch import nn
from torch.nn import functional as F
from d2l import torch as d2l

class Inception(nn.Module):
    def __init__(self, in_channels, c1, c2, c3, c4, **kwargs):
        super(Inception, self).__init__(**kwargs)
        self.p1_1 = nn.Conv2d(in_channels, c1, kernel_size=1)
        self.p2_1 = nn.Conv2d(in_channels, c2[0], kernel_size=1)
        self.p2_2 = nn.Conv2d(c2[0], c2[1], kernel_size=3, padding=1)
        self.p3_1 = nn.Conv2d(in_channels, c3[0], kernel_size=1)
        self.p3_2 = nn.Conv2d(c3[0], c3[1], kernel_size=5, padding=2)
        self.p4_1 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
        self.p4_2 = nn.Conv2d(in_channels, 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)

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.ReLU(),
                   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),
                   nn.AdaptiveAvgPool2d((1, 1)), nn.Flatten())

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

X = torch.rand(size=(1, 1, 96, 96))
for layer in net:
    X = layer(X)
    print(layer.__class__.__name__, 'output shape:\t', X.shape)

lr, num_epochs, batch_size = 0.1, 10, 128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=96)
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())