Dataehale_PyTorch Task4

【Task4】用PyTorch实现多层网络(给代码截图参考)

内容

• 引入模块，读取数据
• 构建计算图（构建网络模型）
• 损失函数与优化器
• 开始训练模型
• 对训练的模型预测结果进行评估

流程图

基于字符的RNN分类模型

之前的任务都是使用CNN模型，这一节找一个RNN模型对单词进行分类，官方教材Source。

1. 准备数据

!wget https://download.pytorch.org/tutorial/data.zip
!unzip data.zip
!rm data.zip

--2019-05-18 15:59:17--  https://download.pytorch.org/tutorial/data.zip
Resolving download.pytorch.org (download.pytorch.org)... 54.230.71.12, 54.230.71.76, 54.230.71.88, ...
Connecting to download.pytorch.org (download.pytorch.org)|54.230.71.12|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 2882130 (2.7M) [application/zip]
Saving to: 'data.zip'
data.zip            100%[===================>]   2.75M   623KB/s    in 4.5s    
2019-05-18 15:59:22 (622 KB/s) - 'data.zip' saved [2882130/2882130]
Archive:  data.zip
   creating: data/
  inflating: data/eng-fra.txt        
   creating: data/names/
  inflating: data/names/Arabic.txt   
  inflating: data/names/Chinese.txt  
  inflating: data/names/Czech.txt    
  inflating: data/names/Dutch.txt    
  inflating: data/names/English.txt  
  inflating: data/names/French.txt   
  inflating: data/names/German.txt   
  inflating: data/names/Greek.txt    
  inflating: data/names/Irish.txt    
  inflating: data/names/Italian.txt  
  inflating: data/names/Japanese.txt  
  inflating: data/names/Korean.txt   
  inflating: data/names/Polish.txt   
  inflating: data/names/Portuguese.txt  
  inflating: data/names/Russian.txt  
  inflating: data/names/Scottish.txt  
  inflating: data/names/Spanish.txt  
  inflating: data/names/Vietnamese.txt

2. 编码转换

def unicodeToAscii(s):
    return ''.join(
        c for c in unicodedata.normalize('NFD', s)
        if unicodedata.category(c) != 'Mn'
        and c in all_letters)

3. 数据读取

# Build the category_lines dictionary, a list of names per language
category_lines = {}
all_categories = []
# Read a file and split into lines
def readLines(filename):
    lines = open(filename, encoding='utf-8').read().strip().split('\n')
    return [unicodeToAscii(line) for line in lines]
for filename in glob.glob('data/names/*.txt'):
    category = os.path.splitext(os.path.basename(filename))[0]
    all_categories.append(category)
    lines = readLines(filename)
    category_lines[category] = lines
n_categories = len(all_categories)

4. 转换到Tensor

import torch
# Find letter index from all_letters, e.g. "a" = 0
def letterToIndex(letter):
    return all_letters.find(letter)
# Just for demonstration, turn a letter into a <1 x n_letters> Tensor
def letterToTensor(letter):
    tensor = torch.zeros(1, n_letters)
    tensor[0][letterToIndex(letter)] = 1
    return tensor
# Turn a line into a <line_length x 1 x n_letters>,
# or an array of one-hot letter vectors
def lineToTensor(line):
    tensor = torch.zeros(len(line), 1, n_letters)
    for li, letter in enumerate(line):
        tensor[li][0][letterToIndex(letter)] = 1
    return tensor
print(letterToTensor('J'))
print(lineToTensor('Jones').size())

5. 创建计算图
   输入经过两层全连接层和一层softmax之后输出所有类别的logits值。

import torch.nn as nn
class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(RNN, self).__init__()
        self.hidden_size = hidden_size
        self.i2h = nn.Linear(input_size + hidden_size, hidden_size)
        self.i2o = nn.Linear(input_size + hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=1)
    def forward(self, input, hidden):
        combined = torch.cat((input, hidden), 1)
        hidden = self.i2h(combined)
        output = self.i2o(combined)
        output = self.softmax(output)
        return output, hidden
    def initHidden(self):
        return torch.zeros(1, self.hidden_size)
n_hidden = 128
rnn = RNN(n_letters, n_hidden, n_categories)

6. 验证计算图前向输出

input = letterToTensor('A')
hidden =torch.zeros(1, n_hidden)
output, next_hidden = rnn(input, hidden)

7. util工具

import random
def categoryFromOutput(output):
    top_n, top_i = output.topk(1)
    category_i = top_i[0].item()
    return all_categories[category_i], category_i
def randomChoice(l):
    return l[random.randint(0, len(l) - 1)]
def randomTrainingExample():
    category = randomChoice(all_categories)
    line = randomChoice(category_lines[category])
    category_tensor = torch.tensor([all_categories.index(category)], dtype=torch.long)
    line_tensor = lineToTensor(line)
    return category, line, category_tensor, line_tensor

8. 损失函数

criterion = nn.NLLLoss()

9. 训练

learning_rate = 0.005 # If you set this too high, it might explode. If too low, it might not learn
def train(category_tensor, line_tensor):
    hidden = rnn.initHidden()
    rnn.zero_grad()
    for i in range(line_tensor.size()[0]):
        output, hidden = rnn(line_tensor[i], hidden)
    loss = criterion(output, category_tensor)
    loss.backward()
    # Add parameters' gradients to their values, multiplied by learning rate
    for p in rnn.parameters():
        p.data.add_(-learning_rate, p.grad.data)
    return output, loss.item()

10. 训练过程

import time
import math
n_iters = 100000
print_every = 5000
plot_every = 1000

# Keep track of losses for plotting
current_loss = 0
all_losses = []
def timeSince(since):
    now = time.time()
    s = now - since
    m = math.floor(s / 60)
    s -= m * 60
    return '%dm %ds' % (m, s)
start = time.time()
for iter in range(1, n_iters + 1):
    category, line, category_tensor, line_tensor = randomTrainingExample()
    output, loss = train(category_tensor, line_tensor)
    current_loss += loss
    # Print iter number, loss, name and guess
    if iter % print_every == 0:
        guess, guess_i = categoryFromOutput(output)
        correct = '✓' if guess == category else '✗ (%s)' % category
        print('%d %d%% (%s) %.4f %s / %s %s' % (iter, iter / n_iters * 100, timeSince(start), loss, line, guess, correct))
    # Add current loss avg to list of losses
    if iter % plot_every == 0:
        all_losses.append(current_loss / plot_every)
        current_loss = 0

5000 5% (0m 25s) 2.8566 Feldt / English ✗ (German)
10000 10% (0m 34s) 3.3638 Petersen / Dutch ✗ (Czech)
15000 15% (0m 43s) 2.8524 Haanraads / Japanese ✗ (Dutch)
20000 20% (0m 51s) 3.1859 Matsigura / Japanese ✗ (Russian)
25000 25% (1m 0s) 1.9056 Kosmatka / Japanese ✗ (Polish)
30000 30% (1m 10s) 4.7566 Marubeni / Italian ✗ (Japanese)
35000 35% (1m 19s) 0.3248 Choe / Korean ✓
40000 40% (1m 29s) 0.0393 Pantelakos / Greek ✓
45000 45% (1m 38s) 4.2054 Masson / Scottish ✗ (French)
50000 50% (1m 47s) 3.5269 Sorge / English ✗ (German)
55000 55% (1m 58s) 1.4175 Almeida / Portuguese ✓
60000 60% (2m 9s) 3.1973 Munro / Italian ✗ (Scottish)
65000 65% (2m 19s) 0.1530 Dalianis / Greek ✓
70000 70% (2m 28s) nan Finn / Polish ✗ (Irish)
75000 75% (2m 38s) nan Jamieson / Polish ✗ (Scottish)
80000 80% (2m 47s) nan Keene / Polish ✗ (English)
85000 85% (2m 56s) nan Iwakura / Polish ✗ (Japanese)
90000 90% (3m 4s) nan Sparacello / Polish ✗ (Italian)
95000 95% (3m 13s) nan Berg / Polish ✗ (Dutch)
100000 100% (3m 23s) nan Acquarone / Polish ✗ (Italian)

11. 训练loss图示

%matplotlib inline
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
plt.figure()
plt.plot(all_losses)

12. 输出测试结果

# Keep track of correct guesses in a confusion matrix
confusion = torch.zeros(n_categories, n_categories)
n_confusion = 10000
# Just return an output given a line
def evaluate(line_tensor):
    hidden = rnn.initHidden()
    for i in range(line_tensor.size()[0]):
        output, hidden = rnn(line_tensor[i], hidden)
    return output
# Go through a bunch of examples and record which are correctly guessed
for i in range(n_confusion):
    category, line, category_tensor, line_tensor = randomTrainingExample()
    output = evaluate(line_tensor)
    guess, guess_i = categoryFromOutput(output)
    category_i = all_categories.index(category)
    confusion[category_i][guess_i] += 1
# Normalize by dividing every row by its sum
for i in range(n_categories):
    confusion[i] = confusion[i] / confusion[i].sum()
# Set up plot
fig = plt.figure()
ax = fig.add_subplot(111)
cax = ax.matshow(confusion.numpy())
fig.colorbar(cax)
# Set up axes
ax.set_xticklabels([''] + all_categories, rotation=90)
ax.set_yticklabels([''] + all_categories)
# Force label at every tick
ax.xaxis.set_major_locator(ticker.MultipleLocator(1))
ax.yaxis.set_major_locator(ticker.MultipleLocator(1))
# sphinx_gallery_thumbnail_number = 2
plt.show()