Task 1

线性回归

从零开始代码

# import 包与模块
%matplotlib inline
import torch
from IPython import display
from matplotlib import pyplot as plt
import numpy as np
import random

# 设置输入特征数，即每个样本有多少特征
num_inputs = 2
# 设置样本数
num_examples = 1000

# 设置数据真实权重与偏置
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)
plt.scatter(features[:, 1].numpy(), labels.numpy(), 1);
# 迭代是访问集合元素的一种方式。迭代器是一个可以记住遍历的位置的对象。迭代器对象从集合的第一个元素开始访问，直到所有的元素被访问完结束。迭代器只能往前不会后退。
def data_iter(batch_size, features, labels):
    num_examples = len(features)
    indices = list(range(num_examples))
    random.shuffle(indices)  # 随机排列
    for i in range(0, num_examples, batch_size):
        j = torch.LongTensor(indices[i: min(i + batch_size, num_examples)]) # 最后剩下的数据可能不够一整个batch
        yield  features.index_select(0, j), labels.index_select(0, j)
batch_size = 10

# 初始化参数
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)
# torch.mm()为矩阵相乘，torch.mul()为对应位置相乘
def linreg(X, w, b):
    return torch.mm(X, w) + b
def squared_loss(y_hat, y): 
    return (y_hat - y.view(y_hat.size())) ** 2 / 2
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
# 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()))

用pytorch简洁实现

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

Softmax与分类模型

Softmax是网络要完成数据的多分类任务时常使用的一种算法，讲网络输出的结果映射到和为1的0到1之间的概率，映射前后值大小顺序不变。

多层感知机

多个线性隐藏层的堆叠与一个线性层没有区别，无法有效增强网络representation的能力，因此在层与层之间需要引入非线性的映射，即激活函数。
Relu(x) = max(0, x)，占用计算资源最少
sigmoid函数将元素的值变换到0到1之间，在LSTM网络中常用作门控计算函数。
tanh将元素的值映射到-1到+1之间。

Task 2

文本预处理要经过文本读入，分词，建立词典，将词转为索引的步骤。
语言模型的参数就是词的概率以及给定前几个词情况下的条件概率。序列长度增加，计算和存储多个词共同出现的概率的复杂度会呈指数级增加。n元语法通过马尔可夫假设简化模型，马尔科夫假设是指一个词的出现只与前面n个词相关，即n阶马尔可夫链（Markov chain of order n）。
时序数据的采样介绍了随机采样和相邻采样。
随机采样：每次从数据里随机采样一个小批量。其中批量大小batch_size是每个小批量的样本数，num_steps是每个样本所包含的时间步数。在随机采样中，每个样本是原始序列上任意截取的一段序列，相邻的两个随机小批量在原始序列上的位置不一定相毗邻。
相邻采样：在相邻采样中，相邻的两个随机小批量在原始序列上的位置相毗邻。

来源：CSDN

作者：Duncan_yitong

链接：https://blog.csdn.net/Duncan_yitong/article/details/104318996

标签

num

linear

第一次打卡

Task 1

线性回归

Softmax与分类模型

多层感知机

Task 2