动手学深度学习打卡（一）

Task01：线性回归；Softmax与分类模型、多层感知机

Task02：文本预处理；语言模型；循环神经网络基础

一、线性回归

1、优化函数的有以下两个步骤：

• (i)初始化模型参数，一般来说使用随机初始化；
• (ii)我们在数据上迭代多次，通过在负梯度方向移动参数来更新每个参数。

2、矢量计算

#矢量计算
'''
向量相加的一种方法是，将这两个向量按元素逐一做标量加法。
向量相加的另一种方法是，将这两个向量直接做矢量加法。
'''

import torch
import time

#初始化ab
n = 1000
a = torch.ones(n)
b = torch.ones(n)

#example：定义时间类来计算标量加法和矢量加法所需要的时间
class Timer(object):
    def __init__(self):
        self.times = []
        self.start()
    def start(self):
        #开启计时器
        self.start_time = time.time()
    
    def stop(self):
        #stop计时器并将时间差存入list
        self.times.append(time.time() - self.start_time)
        return self.times[-1]
    
    def avg(self):
        return sum(self.times)/len(self.times)
        

#使用for循环来做标量加法，计算消耗时间
timer = Timer()
c = torch.zeros(n)
for i in range(n):
    c[i] = a[i] + b[i]
'%.5f sec' % timer.stop()#result '0.01104 sec'

#使用for循环来做标量加法，计算消耗时间
timer = Timer()
c = torch.zeros(n)
for i in range(n):
    c[i] = a[i] + b[i]
'%.5f sec' % timer.stop()#result '0.01058 sec'速度快一点

3、线性回归模型从零开始实现

#import package and module
%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，下面是用来生成数据的线性关系：

price=𝑤⋅area+𝑤⋅age+𝑏
'''
#set input feature number
num_inputs = 2
# set example number
num_examples = 1000

#set true vweight
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 = 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)

#可视化数据
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)])
        yield features.index_select(0, j), labels.index_select(0, j)

#test
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：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

#training
lr = 0.03
num_epochs = 5

net = linreg
loss = squared_loss

#training
for epoch in range(num_epochs):
    for X, y in data_iter(batch_size, features, labels):
        l = loss(net(X, w, b), y).sum()
        
        l.backward()
        
        sgd([w, b], lr, batch_size)
        
        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())
    print('epoch %d, loss %f' % (epoch + 1, train_l.mean().item()))

w, true_w, b, true_b

4、线性回归-Pytorch版本

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

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

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)

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
)

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

#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)

# 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])

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)

#training
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)

二、Softmax与分类模型