深度学习pytorch

一.一些小的注意事项
1.线性回归基本要素，即是深度学习基本要素

二.pytorch基本函数用法
1.torch.manual_seed(seed)
设定生成随机数的种子，并返回一个torch._C.Generator对象
参数：seed(int or long)种子
2.torch.normal(means,std,out=None)
返回一个张量，包含从给定参数means，std,的离散正态分布中抽取随机数
参数：
3.torch.ones(*sizes,out=None)
生成全一张量

三.线性回归的基本要素
模型，数据集，损失函数，优化函数–随机梯度下降
优化函数的两个步骤：
1.初始化模型参数，一般来说使用随机初始化
2.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

四.矢量计算多采用直接矢量计算

import torch
# init variable a, b as 1000 dimension vector
n = 1000
a = torch.ones(n)#生成全1张量
b = torch.ones(n)
d = a + b
'%.5f sec' % timer.stop()

五. 线性回归模型从0开始的实现
1.引入模块

# import packages and modules
%matplotlib inline
import torch
from IPython import display
from matplotlib import pyplot as plt
import numpy as np
import random

2.生成数据集

# set input feature number 
num_inputs = 2
# set example number
num_examples = 1000#样本数

# 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)#生成1000*2的标准正态分布张量
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)#标签加上一个高斯分布概率密度函数

3.使用图像展示生成的数据

plt.scatter(features[:, 1].numpy(), labels.numpy(), 1);

4.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)

5.输出读取的数据集

batch_size = 10

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

6.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)

7.定义模型

def linreg(X, w, b):
    return torch.mm(X, w) + b

8.定义损失函数

def squared_loss(y_hat, y): 
    return (y_hat - y.view(y_hat.size())) ** 2 / 2

9.定义优化函数

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

10.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()))

w, true_w, b, true_b

六.线性模型使用pytorch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
)

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

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

for param in net.parameters():
    print(param)

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)

经过比较可知使用pytorch实现更为简洁

七.Softmax与分类模型
线性回归预测连续型，softmax预测离散型
softmax简洁实现

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__)

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

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
        )

init.normal_(net.linear.weight, mean=0, std=0.01)
init.constant_(net.linear.bias, val=0)

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')

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)

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

八.多层感知机
多层感知机pytorch实现：

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__)

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)

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)

九.文本预处理
具体过程：：

import collections
import re

def read_time_machine():
    with open('/home/kesci/input/timemachine7163/timemachine.txt', 'r') as f:
        lines = [re.sub('[^a-z]+', ' ', line.strip().lower()) for line in f]
    return lines


lines = read_time_machine()
print('# sentences %d' % len(lines))

def tokenize(sentences, token='word'):
    """Split sentences into word or char tokens"""
    if token == 'word':
        return [sentence.split(' ') for sentence in sentences]
    elif token == 'char':
        return [list(sentence) for sentence in sentences]
    else:
        print('ERROR: unkown token type '+token)

tokens = tokenize(lines)
tokens[0:2]

class Vocab(object):
    def __init__(self, tokens, min_freq=0, use_special_tokens=False):
        counter = count_corpus(tokens)  # : 
        self.token_freqs = list(counter.items())
        self.idx_to_token = []
        if use_special_tokens:
            # padding, begin of sentence, end of sentence, unknown
            self.pad, self.bos, self.eos, self.unk = (0, 1, 2, 3)
            self.idx_to_token += ['', '', '', '']
        else:
            self.unk = 0
            self.idx_to_token += ['']
        self.idx_to_token += [token for token, freq in self.token_freqs
                        if freq >= min_freq and token not in self.idx_to_token]
        self.token_to_idx = dict()
        for idx, token in enumerate(self.idx_to_token):
            self.token_to_idx[token] = idx

    def __len__(self):
        return len(self.idx_to_token)

    def __getitem__(self, tokens):
        if not isinstance(tokens, (list, tuple)):
            return self.token_to_idx.get(tokens, self.unk)
        return [self.__getitem__(token) for token in tokens]

    def to_tokens(self, indices):
        if not isinstance(indices, (list, tuple)):
            return self.idx_to_token[indices]
        return [self.idx_to_token[index] for index in indices]

def count_corpus(sentences):
    tokens = [tk for st in sentences for tk in st]
    return collections.Counter(tokens)  # 返回一个字典，记录每个词的出现次数

for i in range(8, 10):
    print('words:', tokens[i])
    print('indices:', vocab[tokens[i]])

十.语言模型

with open('/home/kesci/input/jaychou_lyrics4703/jaychou_lyrics.txt') as f:
    corpus_chars = f.read()
print(len(corpus_chars))
print(corpus_chars[: 40])
corpus_chars = corpus_chars.replace('\n', ' ').replace('\r', ' ')
corpus_chars = corpus_chars[: 10000]

idx_to_char = list(set(corpus_chars)) # 去重，得到索引到字符的映射
char_to_idx = {char: i for i, char in enumerate(idx_to_char)} # 字符到索引的映射
vocab_size = len(char_to_idx)
print(vocab_size)

corpus_indices = [char_to_idx[char] for char in corpus_chars]  # 将每个字符转化为索引，得到一个索引的序列
sample = corpus_indices[: 20]
print('chars:', ''.join([idx_to_char[idx] for idx in sample]))
print('indices:', sample)

def load_data_jay_lyrics():
    with open('/home/kesci/input/jaychou_lyrics4703/jaychou_lyrics.txt') as f:
        corpus_chars = f.read()
    corpus_chars = corpus_chars.replace('\n', ' ').replace('\r', ' ')
    corpus_chars = corpus_chars[0:10000]
    idx_to_char = list(set(corpus_chars))
    char_to_idx = dict([(char, i) for i, char in enumerate(idx_to_char)])
    vocab_size = len(char_to_idx)
    corpus_indices = [char_to_idx[char] for char in corpus_chars]
    return corpus_indices, char_to_idx, idx_to_char, vocab_size

import torch
import random
def data_iter_random(corpus_indices, batch_size, num_steps, device=None):
    # 减1是因为对于长度为n的序列，X最多只有包含其中的前n - 1个字符
    num_examples = (len(corpus_indices) - 1) // num_steps  # 下取整，得到不重叠情况下的样本个数
    example_indices = [i * num_steps for i in range(num_examples)]  # 每个样本的第一个字符在corpus_indices中的下标
    random.shuffle(example_indices)

    def _data(i):
        # 返回从i开始的长为num_steps的序列
        return corpus_indices[i: i + num_steps]
    if device is None:
        device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    
    for i in range(0, num_examples, batch_size):
        # 每次选出batch_size个随机样本
        batch_indices = example_indices[i: i + batch_size]  # 当前batch的各个样本的首字符的下标
        X = [_data(j) for j in batch_indices]
        Y = [_data(j + 1) for j in batch_indices]
        yield torch.tensor(X, device=device), torch.tensor(Y, device=device)

my_seq = list(range(30))
for X, Y in data_iter_random(my_seq, batch_size=2, num_steps=6):
    print('X: ', X, '\nY:', Y, '\n')

def data_iter_consecutive(corpus_indices, batch_size, num_steps, device=None):
    if device is None:
        device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    corpus_len = len(corpus_indices) // batch_size * batch_size  # 保留下来的序列的长度
    corpus_indices = corpus_indices[: corpus_len]  # 仅保留前corpus_len个字符
    indices = torch.tensor(corpus_indices, device=device)
    indices = indices.view(batch_size, -1)  # resize成(batch_size, )
    batch_num = (indices.shape[1] - 1) // num_steps
    for i in range(batch_num):
        i = i * num_steps
        X = indices[:, i: i + num_steps]
        Y = indices[:, i + 1: i + num_steps + 1]
        yield X, Y

for X, Y in data_iter_consecutive(my_seq, batch_size=2, num_steps=6):
    print('X: ', X, '\nY:', Y, '\n')

十一.循环神经网络基础
简洁实现循环神经网络

rnn_layer = nn.RNN(input_size=vocab_size, hidden_size=num_hiddens)
num_steps, batch_size = 35, 2
X = torch.rand(num_steps, batch_size, vocab_size)
state = None
Y, state_new = rnn_layer(X, state)
print(Y.shape, state_new.shape)

class RNNModel(nn.Module):
    def __init__(self, rnn_layer, vocab_size):
        super(RNNModel, self).__init__()
        self.rnn = rnn_layer
        self.hidden_size = rnn_layer.hidden_size * (2 if rnn_layer.bidirectional else 1) 
        self.vocab_size = vocab_size
        self.dense = nn.Linear(self.hidden_size, vocab_size)

    def forward(self, inputs, state):
        # inputs.shape: (batch_size, num_steps)
        X = to_onehot(inputs, vocab_size)
        X = torch.stack(X)  # X.shape: (num_steps, batch_size, vocab_size)
        hiddens, state = self.rnn(X, state)
        hiddens = hiddens.view(-1, hiddens.shape[-1])  # hiddens.shape: (num_steps * batch_size, hidden_size)
        output = self.dense(hiddens)
        return output, state

def predict_rnn_pytorch(prefix, num_chars, model, vocab_size, device, idx_to_char,
                      char_to_idx):
    state = None
    output = [char_to_idx[prefix[0]]]  # output记录prefix加上预测的num_chars个字符
    for t in range(num_chars + len(prefix) - 1):
        X = torch.tensor([output[-1]], device=device).view(1, 1)
        (Y, state) = model(X, state)  # 前向计算不需要传入模型参数
        if t < len(prefix) - 1:
            output.append(char_to_idx[prefix[t + 1]])
        else:
            output.append(Y.argmax(dim=1).item())
    return ''.join([idx_to_char[i] for i in output])

model = RNNModel(rnn_layer, vocab_size).to(device)
predict_rnn_pytorch('分开', 10, model, vocab_size, device, idx_to_char, char_to_idx)

def train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
                                corpus_indices, idx_to_char, char_to_idx,
                                num_epochs, num_steps, lr, clipping_theta,
                                batch_size, pred_period, pred_len, prefixes):
    loss = nn.CrossEntropyLoss()
    optimizer = torch.optim.Adam(model.parameters(), lr=lr)
    model.to(device)
    for epoch in range(num_epochs):
        l_sum, n, start = 0.0, 0, time.time()
        data_iter = d2l.data_iter_consecutive(corpus_indices, batch_size, num_steps, device) # 相邻采样
        state = None
        for X, Y in data_iter:
            if state is not None:
                # 使用detach函数从计算图分离隐藏状态
                if isinstance (state, tuple): # LSTM, state:(h, c)  
                    state[0].detach_()
                    state[1].detach_()
                else: 
                    state.detach_()
            (output, state) = model(X, state) # output.shape: (num_steps * batch_size, vocab_size)
            y = torch.flatten(Y.T)
            l = loss(output, y.long())
            
            optimizer.zero_grad()
            l.backward()
            grad_clipping(model.parameters(), clipping_theta, device)
            optimizer.step()
            l_sum += l.item() * y.shape[0]
            n += y.shape[0]
        

        if (epoch + 1) % pred_period == 0:
            print('epoch %d, perplexity %f, time %.2f sec' % (
                epoch + 1, math.exp(l_sum / n), time.time() - start))
            for prefix in prefixes:
                print(' -', predict_rnn_pytorch(
                    prefix, pred_len, model, vocab_size, device, idx_to_char,
                    char_to_idx))

num_epochs, batch_size, lr, clipping_theta = 250, 32, 1e-3, 1e-2
pred_period, pred_len, prefixes = 50, 50, ['分开', '不分开']
train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
                            corpus_indices, idx_to_char, char_to_idx,
                            num_epochs, num_steps, lr, clipping_theta,
                            batch_size, pred_period, pred_len, prefixes)