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')