소스코드 원본 링크 : https://pytorch.org/tutorials/intermediate/char_rnn_generation_tutorial.html
전반적으로 이전에 작성했던 글과 코드가 유사하여 자세한건 skip
Preparing the Data
Classifying Names 에서 사용했던 함수와 동일하다. 유니코드를 아스키코드로, 카테고리와 라인(단어)에 대한 선처리를 해주는 코드이다.
from __future__ import unicode_literals, print_function, division
from io import open
import glob
import os
import unicodedata
import string
all_letters = string.ascii_letters + " .,;'-"
n_letters = len(all_letters) + 1 # Plus EOS marker
def findFiles(path): return glob.glob(path)
# Turn a Unicode string to plain ASCII, thanks to http://stackoverflow.com/a/518232/2809427
def unicodeToAscii(s):
return ''.join(
c for c in unicodedata.normalize('NFD', s)
if unicodedata.category(c) != 'Mn'
and c in all_letters
)
# 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]
# Build the category_lines dictionary, a list of lines per category
category_lines = {}
all_categories = []
for filename in findFiles('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)
if n_categories == 0:
raise RuntimeError('Data not found. Make sure that you downloaded data '
'from https://download.pytorch.org/tutorial/data.zip and extract it to '
'the current directory.')
print('# categories:', n_categories, all_categories)
print(unicodeToAscii("O'Néàl"))
Creating the Network
분류(Classifying)와 생성(Generating) 문제의 네트워크 차이점을 코드에서 확인해볼 수 있다. category_tensor가 입력에 들어간다는 점, combined가 2번 이뤄진다는 점, dropout을 한다는 점을 확인해보자.
import torch
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(n_categories + input_size + hidden_size, hidden_size)
self.i2o = nn.Linear(n_categories + input_size + hidden_size, output_size)
self.o2o = nn.Linear(hidden_size + output_size, output_size)
self.dropout = nn.Dropout(0.1)
self.softmax = nn.LogSoftmax(dim=1)
def forward(self, category, input, hidden):
input_combined = torch.cat((category, input, hidden), 1)
hidden = self.i2h(input_combined)
output = self.i2o(input_combined)
output_combined = torch.cat((hidden, output), 1)
output = self.o2o(output_combined)
output = self.dropout(output)
output = self.softmax(output)
return output, hidden
def initHidden(self):
return torch.zeros(1, self.hidden_size)
Preparing for Training
무작위의 카테고리를 하나 고르고 그 카테고리의 무작위 이름을 하나 골라서 pair로 리턴한다.
import random
# Random item from a list
def randomChoice(l):
return l[random.randint(0, len(l) - 1)]
# Get a random category and random line from that category
def randomTrainingPair():
category = randomChoice(all_categories)
line = randomChoice(category_lines[category])
return category, line
categoryTensor : 카테고리를 텐서로 반환해준다.
inputTensor: Input을 one-hot matrix 텐서로 반환해준다.
targetTensor: target index 리스트를 텐서로 반환해준다.
# One-hot vector for category
def categoryTensor(category):
li = all_categories.index(category)
tensor = torch.zeros(1, n_categories)
tensor[0][li] = 1
return tensor
# One-hot matrix of first to last letters (not including EOS) for input
def inputTensor(line):
tensor = torch.zeros(len(line), 1, n_letters)
for li in range(len(line)):
letter = line[li]
tensor[li][0][all_letters.find(letter)] = 1
return tensor
# LongTensor of second letter to end (EOS) for target
def targetTensor(line):
letter_indexes = [all_letters.find(line[li]) for li in range(1, len(line))]
letter_indexes.append(n_letters - 1) # EOS
return torch.LongTensor(letter_indexes)
무작위의 카테고리 텐서, 입력 텐서, 타겟 텐서를 반환한다.
# Make category, input, and target tensors from a random category, line pair
def randomTrainingExample():
category, line = randomTrainingPair()
category_tensor = categoryTensor(category)
input_line_tensor = inputTensor(line)
target_line_tensor = targetTensor(line)
return category_tensor, input_line_tensor, target_line_tensor
Training the Network
분류문제에서의 학습 메소드와 유사하다. target_line_tensor를 파라미터로 받은 후 데이터 차원을 맞추기위해 unsqueeze를 한번 실행한 것을 확인할 수 있다.
criterion = nn.NLLLoss()
learning_rate = 0.0005
def train(category_tensor, input_line_tensor, target_line_tensor):
target_line_tensor.unsqueeze_(-1)
hidden = rnn.initHidden()
rnn.zero_grad()
loss = 0
for i in range(input_line_tensor.size(0)):
output, hidden = rnn(category_tensor, input_line_tensor[i], hidden)
l = criterion(output, target_line_tensor[i])
loss += l
loss.backward()
for p in rnn.parameters():
p.data.add_(-learning_rate, p.grad.data)
return output, loss.item() / input_line_tensor.size(0)
Time Tracking
import time
import math
def timeSince(since):
now = time.time()
s = now - since
m = math.floor(s / 60)
s -= m * 60
return '%dm %ds' % (m, s)
RNN을 학습하고 시간, 학습진행률, 손실 등을 출력해주는 코드.
rnn = RNN(n_letters, 128, n_letters)
n_iters = 100000
print_every = 5000
plot_every = 500
all_losses = []
total_loss = 0 # Reset every plot_every iters
start = time.time()
for iter in range(1, n_iters + 1):
output, loss = train(*randomTrainingExample())
total_loss += loss
if iter % print_every == 0:
print('%s (%d %d%%) %.4f' % (timeSince(start), iter, iter / n_iters * 100, loss))
if iter % plot_every == 0:
all_losses.append(total_loss / plot_every)
total_loss = 0
Plotting the Losses
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
plt.figure()
plt.plot(all_losses)
Sampling the Network
다음과 같은 과정을 거친다.
- Create tensors for input category, starting letter, and empty hidden state
- Create a string
output_name
with the starting letter - Up to a maximum output length,
- Feed the current letter to the network
- Get the next letter from highest output, and next hidden state
- If the letter is EOS, stop here
- If a regular letter, add to
output_name
and continue
- Return the final name
max_length = 20
# Sample from a category and starting letter
def sample(category, start_letter='A'):
with torch.no_grad(): # no need to track history in sampling
category_tensor = categoryTensor(category)
input = inputTensor(start_letter)
hidden = rnn.initHidden()
output_name = start_letter
for i in range(max_length):
output, hidden = rnn(category_tensor, input[0], hidden)
topv, topi = output.topk(1)
topi = topi[0][0]
if topi == n_letters - 1:
break
else:
letter = all_letters[topi]
output_name += letter
input = inputTensor(letter)
return output_name
# Get multiple samples from one category and multiple starting letters
def samples(category, start_letters='ABC'):
for start_letter in start_letters:
print(sample(category, start_letter))
samples('Russian', 'RUS')
samples('German', 'GER')
samples('Spanish', 'SPA')
samples('Chinese', 'CHI')