《动手学深度学习》Pytorch版学习笔记（一）：Task01

课程背景

在疫情的影响下，不少学校已经做出了延迟开学的决定，：伯禹教育、Datawhale、和鲸科技牵头与多家AI企业合作，让在家的同学也能免费学习优质的付费课程，同时为学习者创建好的学习环境，提供就业绿色通道。

主修课程

《动手学深度学习》 代码讲解Pytorch版：该书是2019年国内最受欢迎的人工智能学习教材之一，是一本面向中文读者的能运行、可讨论的深度学习教科书，书籍作者之一亚马逊首席科学家李沐，毕业于上海交大。伯禹教育携手上海交通大学团队，基于此书籍，将其中的代码框架由MXNET迁移至PyTorch，并对这些代码制作了讲解视频。帮助大家边动手写代码边巩固理论知识，从原理到实践，上手深度学习。

1 任务

【第一次打卡】内容（2月11日-14日）
Task01：线性回归；Softmax与分类模型、多层感知机（1天）
Task02：过拟合、欠拟合及其解决方案；梯度消失、梯度爆炸、梯度偏移；卷积神经网络基础（1天）
Task03：LeNet；卷积神经网络进阶；批量归一化和残差网络（1天）
打卡时间：【2020-02-11 08:00 -- 2020-02-14 22:00】
打卡链接：学习开始放出

2 线性回归

2.1 线性回归的基本要素

这里就不对线性回归的概念进行展开介绍了，具体概念可见：伯禹学习平台

2.2 线性回归模型从零开始的实现

# 导入包
%matplotlib inline
import torch
from IPython import display
from matplotlib import pyplot as plt
import numpy as np
import random

print(torch.__version__)

#生成数据集：使用线性模型来生成数据集，生成一个1000个样本的数据集
# set input feature number 
num_inputs = 2
# set example number
num_examples = 1000

# set true weight and bias in order to generate corresponded label
true_w = [2, -3.4]
true_b = 4.2

features = torch.randn(num_examples, num_inputs,
                      dtype=torch.float32)
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()),
                       dtype=torch.float32)

#使用图像来展示生成的数据
plt.scatter(features[:, 1].numpy(), labels.numpy(), 1);

#读取数据集
def data_iter(batch_size, features, labels):
    num_examples = len(features)
    indices = list(range(num_examples))
    random.shuffle(indices)  # random read 10 samples
    for i in range(0, num_examples, batch_size):
        j = torch.LongTensor(indices[i: min(i + batch_size, num_examples)]) # the last time may be not enough for a whole batch
        yield  features.index_select(0, j), labels.index_select(0, j)

batch_size = 10

for X, y in data_iter(batch_size, features, labels):
    print(X, '\n', y)
    break

#初始化模型参数
w = torch.tensor(np.random.normal(0, 0.01, (num_inputs, 1)), dtype=torch.float32)
b = torch.zeros(1, dtype=torch.float32)

w.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)

#定义模型
def linreg(X, w, b):
    return torch.mm(X, w) + b

#定义损失函数：用均方误差损失函数
def squared_loss(y_hat, y): 
    return (y_hat - y.view(y_hat.size())) ** 2 / 2

#定义优化函数：使用小批量随机梯度下降
def sgd(params, lr, batch_size): 
    for param in params:
        param.data -= lr * param.grad / batch_size # ues .data to operate param without gradient track

#训练
# super parameters init
lr = 0.03
num_epochs = 5

net = linreg
loss = squared_loss

# training
for epoch in range(num_epochs):  # training repeats num_epochs times
    # in each epoch, all the samples in dataset will be used once
    
    # X is the feature and y is the label of a batch sample
    for X, y in data_iter(batch_size, features, labels):
        l = loss(net(X, w, b), y).sum()  
        # calculate the gradient of batch sample loss 
        l.backward()  
        # using small batch random gradient descent to iter model parameters
        sgd([w, b], lr, batch_size)  
        # reset parameter gradient
        w.grad.data.zero_()
        b.grad.data.zero_()
    train_l = loss(net(features, w, b), labels)
    print('epoch %d, loss %f' % (epoch + 1, train_l.mean().item()))

2.3 线性回归模型使用pytorch的简洁实现

#导入包
import torch
from torch import nn
import numpy as np
torch.manual_seed(1)

print(torch.__version__)
torch.set_default_tensor_type('torch.FloatTensor')

#生成数据集：在这里生成数据集跟从零开始的实现中是完全一样的。
num_inputs = 2
num_examples = 1000

true_w = [2, -3.4]
true_b = 4.2

features = torch.tensor(np.random.normal(0, 1, (num_examples, num_inputs)), dtype=torch.float)
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()), dtype=torch.float)

#读取数据集
import torch.utils.data as Data

batch_size = 10

# combine featues and labels of dataset
dataset = Data.TensorDataset(features, labels)

# put dataset into DataLoader
data_iter = Data.DataLoader(
    dataset=dataset,            # torch TensorDataset format
    batch_size=batch_size,      # mini batch size
    shuffle=True,               # whether shuffle the data or not
    num_workers=2,              # read data in multithreading
)

#定义模型
class LinearNet(nn.Module):
    def __init__(self, n_feature):
        super(LinearNet, self).__init__()      # call father function to init 
        self.linear = nn.Linear(n_feature, 1)  # function prototype: `torch.nn.Linear(in_features, out_features, bias=True)`

    def forward(self, x):
        y = self.linear(x)
        return y
    
net = LinearNet(num_inputs)
print(net)

# ways to init a multilayer network
# method one
net = nn.Sequential(
    nn.Linear(num_inputs, 1)
    # other layers can be added here
    )

# method two
net = nn.Sequential()
net.add_module('linear', nn.Linear(num_inputs, 1))
# net.add_module ......

# method three
from collections import OrderedDict
net = nn.Sequential(OrderedDict([
          ('linear', nn.Linear(num_inputs, 1))
          # ......
        ]))

print(net)
print(net[0])

#初始化模型参数
from torch.nn import init

init.normal_(net[0].weight, mean=0.0, std=0.01)
init.constant_(net[0].bias, val=0.0)  # or you can use `net[0].bias.data.fill_(0)` to modify it directly
for param in net.parameters():
    print(param)

#定义损失函数
loss = nn.MSELoss()    # nn built-in squared loss function
                       # function prototype: `torch.nn.MSELoss(size_average=None, reduce=None, reduction='mean')`

#定义优化函数
import torch.optim as optim

optimizer = optim.SGD(net.parameters(), lr=0.03)   # built-in random gradient descent function
print(optimizer)  # function prototype: `torch.optim.SGD(params, lr=, momentum=0, dampening=0, weight_decay=0, nesterov=False)`

#训练
num_epochs = 3
for epoch in range(1, num_epochs + 1):
    for X, y in data_iter:
        output = net(X)
        l = loss(output, y.view(-1, 1))
        optimizer.zero_grad() # reset gradient, equal to net.zero_grad()
        l.backward()
        optimizer.step()
    print('epoch %d, loss: %f' % (epoch, l.item()))

# result comparision
dense = net[0]
print(true_w, dense.weight.data)
print(true_b, dense.bias.data)

2.4 两种实现方式的比较

1. 从零开始的实现（推荐用来学习）能够更好的理解模型和神经网络底层的原理；
2. 使用pytorch的简洁实现能够更加快速地完成模型的设计与实现。

3 softmax和分类模型

3.1 softmax回归的基本概念

这里就不对概念进行展开介绍了，具体概念可见：伯禹学习平台

3.2 如何获取Fashion-MNIST数据集和读取数据

在介绍softmax回归的实现前我们先引入一个多类图像分类数据集。它将在后面的章节中被多次使用，以方便我们观察比较算法之间在模型精度和计算效率上的区别。图像分类数据集中最常用的是手写数字识别数据集MNIST[1]。但大部分模型在MNIST上的分类精度都超过了95%。为了更直观地观察算法之间的差异，我们将使用一个图像内容更加复杂的数据集Fashion-MNIST[2]。

我这里我们会使用torchvision包，它是服务于PyTorch深度学习框架的，主要用来构建计算机视觉模型。torchvision主要由以下几部分构成：

1. torchvision.datasets: 一些加载数据的函数及常用的数据集接口；
2. torchvision.models: 包含常用的模型结构（含预训练模型），例如AlexNet、VGG、ResNet等；
3. torchvision.transforms: 常用的图片变换，例如裁剪、旋转等；
4. torchvision.utils: 其他的一些有用的方法。

#导入包
# import needed package
%matplotlib inline
from IPython import display
import matplotlib.pyplot as plt

import torch
import torchvision
import torchvision.transforms as transforms
import time

import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l

print(torch.__version__)
print(torchvision.__version__)

# 本函数已保存在d2lzh包中方便以后使用
def get_fashion_mnist_labels(labels):
    text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat',
                   'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot']
    return [text_labels[int(i)] for i in labels]

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()

# 读取数据
batch_size = 256
num_workers = 4
train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers)
test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers)

3.3 softmax回归模型的从零开始实现

import torch
import torchvision
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l

print(torch.__version__)
print(torchvision.__version__)

#获取训练集数据和测试集数据
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

#模型参数初始化
num_inputs = 784
print(28*28)
num_outputs = 10

W = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_outputs)), dtype=torch.float)
b = torch.zeros(num_outputs, dtype=torch.float)

#对多维Tensor按维度操作
X = torch.tensor([[1, 2, 3], [4, 5, 6]])
print(X.sum(dim=0, keepdim=True))  # dim为0，按照相同的列求和，并在结果中保留列特征
print(X.sum(dim=1, keepdim=True))  # dim为1，按照相同的行求和，并在结果中保留行特征
print(X.sum(dim=0, keepdim=False)) # dim为0，按照相同的列求和，不在结果中保留列特征
print(X.sum(dim=1, keepdim=False)) # dim为1，按照相同的行求和，不在结果中保留行特征

#定义softmax操作
def softmax(X):
    X_exp = X.exp()
    partition = X_exp.sum(dim=1, keepdim=True)
    # print("X size is ", X_exp.size())
    # print("partition size is ", partition, partition.size())
    return X_exp / partition  # 这里应用了广播机制

#softmax回归模型
def net(X):
    return softmax(torch.mm(X.view((-1, num_inputs)), W) + b)

#定义损失函数
y_hat = torch.tensor([[0.1, 0.3, 0.6], [0.3, 0.2, 0.5]])
y = torch.LongTensor([0, 2])
y_hat.gather(1, y.view(-1, 1))

def cross_entropy(y_hat, y):
    return - torch.log(y_hat.gather(1, y.view(-1, 1)))

#定义准确率
def accuracy(y_hat, y):
    return (y_hat.argmax(dim=1) == y).float().mean().item()

# 本函数已保存在d2lzh_pytorch包中方便以后使用。该函数将被逐步改进：它的完整实现将在“图像增广”一节中描述
def evaluate_accuracy(data_iter, net):
    acc_sum, n = 0.0, 0
    for X, y in data_iter:
        acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
        n += y.shape[0]
    return acc_sum / n

#训练模型
num_epochs, lr = 5, 0.1

# 本函数已保存在d2lzh_pytorch包中方便以后使用
def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
              params=None, lr=None, optimizer=None):
    for epoch in range(num_epochs):
        train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
        for X, y in train_iter:
            y_hat = net(X)
            l = loss(y_hat, y).sum()
            
            # 梯度清零
            if optimizer is not None:
                optimizer.zero_grad()
            elif params is not None and params[0].grad is not None:
                for param in params:
                    param.grad.data.zero_()
            
            l.backward()
            if optimizer is None:
                d2l.sgd(params, lr, batch_size)
            else:
                optimizer.step() 
            
            
            train_l_sum += l.item()
            train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
            n += y.shape[0]
        test_acc = evaluate_accuracy(test_iter, net)
        print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
              % (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))

train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, batch_size, [W, b], lr)

#模型预测
X, y = iter(test_iter).next()

true_labels = d2l.get_fashion_mnist_labels(y.numpy())
pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(dim=1).numpy())
titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]

d2l.show_fashion_mnist(X[0:9], titles[0:9])

3.4 使用pytorch重新实现softmax回归模型

# 加载各种包或者模块
import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l

print(torch.__version__)

#初始化参数和获取数据
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

#定义网络模型
num_inputs = 784
num_outputs = 10

class LinearNet(nn.Module):
    def __init__(self, num_inputs, num_outputs):
        super(LinearNet, self).__init__()
        self.linear = nn.Linear(num_inputs, num_outputs)
    def forward(self, x): # x 的形状: (batch, 1, 28, 28)
        y = self.linear(x.view(x.shape[0], -1))
        return y
    
# net = LinearNet(num_inputs, num_outputs)

class FlattenLayer(nn.Module):
    def __init__(self):
        super(FlattenLayer, self).__init__()
    def forward(self, x): # x 的形状: (batch, *, *, ...)
        return x.view(x.shape[0], -1)

from collections import OrderedDict
net = nn.Sequential(
        # FlattenLayer(),
        # LinearNet(num_inputs, num_outputs) 
        OrderedDict([
           ('flatten', FlattenLayer()),
           ('linear', nn.Linear(num_inputs, num_outputs))]) # 或者写成我们自己定义的 LinearNet(num_inputs, num_outputs) 也可以
        )

#初始化模型参数
init.normal_(net.linear.weight, mean=0, std=0.01)
init.constant_(net.linear.bias, val=0)

#定义损失函数
loss = nn.CrossEntropyLoss() # 下面是他的函数原型
# class torch.nn.CrossEntropyLoss(weight=None, size_average=None, ignore_index=-100, reduce=None, reduction='mean')

#定义优化函数
optimizer = torch.optim.SGD(net.parameters(), lr=0.1) # 下面是函数原型
# class torch.optim.SGD(params, lr=, momentum=0, dampening=0, weight_decay=0, nesterov=False)

#训练
num_epochs = 5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)

4 多层感知机

4.1 多层感知机的基本知识

这里就不对概念进行展开介绍了，具体概念可见：伯禹学习平台

4.2 使用多层感知机图像分类的从零开始的实现

#导入包
import torch
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l

#获取训练集
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size,root='/home/kesci/input/FashionMNIST2065')

#定义模型参数
num_inputs, num_outputs, num_hiddens = 784, 10, 256

W1 = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_hiddens)), dtype=torch.float)
b1 = torch.zeros(num_hiddens, dtype=torch.float)
W2 = torch.tensor(np.random.normal(0, 0.01, (num_hiddens, num_outputs)), dtype=torch.float)
b2 = torch.zeros(num_outputs, dtype=torch.float)

params = [W1, b1, W2, b2]
for param in params:
    param.requires_grad_(requires_grad=True)

#定义激活函数
def relu(X):
    return torch.max(input=X, other=torch.tensor(0.0))

#定义网络
def net(X):
    X = X.view((-1, num_inputs))
    H = relu(torch.matmul(X, W1) + b1)
    return torch.matmul(H, W2) + b2

#定义损失函数
loss = torch.nn.CrossEntropyLoss()

#训练
num_epochs, lr = 5, 100.0
# def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
#               params=None, lr=None, optimizer=None):
#     for epoch in range(num_epochs):
#         train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
#         for X, y in train_iter:
#             y_hat = net(X)
#             l = loss(y_hat, y).sum()
#             
#             # 梯度清零
#             if optimizer is not None:
#                 optimizer.zero_grad()
#             elif params is not None and params[0].grad is not None:
#                 for param in params:
#                     param.grad.data.zero_()
#            
#             l.backward()
#             if optimizer is None:
#                 d2l.sgd(params, lr, batch_size)
#             else:
#                 optimizer.step()  # “softmax回归的简洁实现”一节将用到
#             
#             
#             train_l_sum += l.item()
#             train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
#             n += y.shape[0]
#         test_acc = evaluate_accuracy(test_iter, net)
#         print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
#               % (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))

d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params, lr)

4.3 使用pytorch的简洁实现

#导入包
import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l

#初始化模型和各个参数
num_inputs, num_outputs, num_hiddens = 784, 10, 256
    
net = nn.Sequential(
        d2l.FlattenLayer(),
        nn.Linear(num_inputs, num_hiddens),
        nn.ReLU(),
        nn.Linear(num_hiddens, num_outputs), 
        )
    
for params in net.parameters():
    init.normal_(params, mean=0, std=0.01)

#训练
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size,root='/home/kesci/input/FashionMNIST2065')
loss = torch.nn.CrossEntropyLoss()

optimizer = torch.optim.SGD(net.parameters(), lr=0.5)

num_epochs = 5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)