train_pt.py

# This tutorial is adapted from https://pytorch.org/tutorials/intermediate/char_rnn_generation_tutorial.html

from __future__ import unicode_literals, print_function, division
from io import open
import glob
import os
import unicodedata
import string
import random

import torch
import torch.nn as nn


## read data
all_letters = string.ascii_letters + " .,;'-"
n_letters = len(all_letters) + 1 # Plus EOS marker

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

category_lines = {}
all_categories = []
for filename in glob.glob('data/names/*.txt'):
    category = os.path.splitext(os.path.basename(filename))[0]
    all_categories.append(category)    
    with open(filename, encoding='utf-8') as some_file:
        lines = [unicodeToAscii(line.strip()) for line in some_file]
    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"))


## network
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)


## training
def categoryTensor(category): # One-hot vector for category
    li = all_categories.index(category)
    tensor = torch.zeros(1, n_categories)
    tensor[0][li] = 1
    return tensor

def inputTensor(line): # One-hot matrix of first to last letters (not including EOS) for input
    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

def randomTrainingExample(): # Make category, input, and target tensors from a random category, line pair
    category = all_categories[random.randint(0, len(all_categories) - 1)]
    line = category_lines[category][random.randint(0, len(category_lines[category]) - 1)]
    category_tensor = categoryTensor(category)
    input_line_tensor = inputTensor(line)
    letter_indexes = [all_letters.find(line[li]) for li in range(1, len(line))]
    letter_indexes.append(n_letters - 1) # EOS
    target_line_tensor = torch.LongTensor(letter_indexes)
    return category_tensor, input_line_tensor, target_line_tensor

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_(p.grad.data, alpha=-learning_rate)
    return output, loss.item() / input_line_tensor.size(0)

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
for iter in range(1, n_iters + 1):
    output, loss = train(*randomTrainingExample())
    # monitoring training
    total_loss += loss
    if iter % print_every == 0:
        print('(%d %d%%) %.4f' % (iter, iter/n_iters*100, loss))
    if iter % plot_every == 0:
        all_losses.append(total_loss / plot_every)
        total_loss = 0


## generate
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)
            _, 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', 'RUSSIAN')
samples('German', 'GERMAN')
samples('Spanish', 'SPANISH')
samples('Chinese', 'CHINESE')