Pytorch实现基于CharRNN的文本分类与生成示例

import torch
from torch import nn

embedding = nn.Embedding(5, 4) # 假定语料只有5个词，词向量维度为3
sents = [[1, 2, 3], 
   [2, 3, 4]] # 两个句子，how:1 are:2 you:3, are:2 you:3 ok:4
embed = embedding(torch.LongTensor(sents))
print(embed) # shape=(2
'''
tensor([[[-0.6991, -0.3340, -0.7701, -0.6255],
   [ 0.2969, 0.4720, -0.9403, 0.2982],
   [ 0.8902, -1.0681, 0.4035, 0.1645]],
  [[ 0.2969, 0.4720, -0.9403, 0.2982],
   [ 0.8902, -1.0681, 0.4035, 0.1645],
   [-0.7944, -0.1766, -1.5941, 0.4544]]], grad_fn=<EmbeddingBackward>)
'''

import torch
from torch import nn

vocab_size = 5
embed_dim = 3
hidden_dim = 8

embedding = nn.Embedding(vocab_size, embed_dim)
rnn = nn.RNN(embed_dim, hidden_dim, batch_first=True)

sents = [[1, 2, 4], 
   [2, 3, 4]]
h0 = torch.zeros(1, embeded.size(0), 8) # shape=(num_layers*num_directions, batch, hidden_dim)

embeded = embedding(torch.LongTensor(sents))
out, hidden = rnn(embeded, h0) # out.shape=(2,3,8), hidden.shape=(1,2,8)

print(out, hidden) 

'''
tensor([[[-0.1556, -0.2721, 0.1485, -0.2081, -0.2231, -0.1459, -0.0319, 0.2617],
   [-0.0274, 0.1561, -0.0509, -0.1723, -0.2678, -0.2616, 0.0786, 0.4124],
   [ 0.2346, 0.4487, -0.1409, -0.0807, -0.0232, -0.4975, 0.4244, 0.8337]],
  [[ 0.0879, 0.1122, 0.1502, -0.3033, -0.2715, -0.1191, 0.1367, 0.5275],
   [ 0.2258, 0.4395, -0.1365, 0.0135, -0.0777, -0.5221, 0.4683, 0.8115],
   [ 0.0158, 0.3471, 0.0742, -0.0550, -0.0098, -0.5521, 0.5923,0.8782]]],    grad_fn=<TransposeBackward0>) 
tensor([[[ 0.2346, 0.4487, -0.1409, -0.0807, -0.0232, -0.4975, 0.4244, 0.8337],
   [ 0.0158, 0.3471, 0.0742, -0.0550, -0.0098, -0.5521, 0.5923, 0.8782]]],    grad_fn=<ViewBackward>)
'''

import torch
from torch import nn
import torch.nn.functional as F
import numpy as np
import sklearn
import string
import random
nltk.download('names')
from nltk.corpus import names

USE_CUDA = torch.cuda.is_available()
device = torch.device("cuda" if USE_CUDA else "cpu")

chars = string.ascii_lowercase + '-' + ' ' + "'"

'''
将名字编码为向量：每个字符为one-hot编码，将多个字符的向量进行堆叠
abc = [ [1, 0, ...,0]
  [0, 1, 0, ..]
  [0, 0, 1, ..] ]
abc.shape = (len("abc"), len(chars))
'''
def name2vec(name):
 ids = [chars.index(c) for c in name if c not in ["\\"]]

 a = np.zeros(shape=(len(ids), len(chars)))
 for i, idx in enumerate(ids):
  a[i][idx] = 1
 return a


def load_data():
 female_file, male_file = names.fileids()

 f1_names = names.words(female_file)
 f2_names = names.words(male_file)

 data_set = [(name.lower(), 0) for name in f1_names] + [(name.lower(), 1) for name in f2_names]
 data_set = [(name2vec(name), sexy) for name, sexy in data_set]
 random.shuffle(data_set)
 return data_set


class CharRNN(nn.Module):
 def __init__(self, vocab_size, hidden_size, output_size):
  super(CharRNN, self).__init__()
  self.vocab_size = vocab_size
  self.hidden_size = hidden_size
  self.output_size = output_size

  self.rnn = nn.RNN(vocab_size, hidden_size, batch_first=True)
  self.liner = nn.Linear(hidden_size, output_size)

 def forward(self, input):
  h0 = torch.zeros(1, 1, self.hidden_size, device=device) # 初始hidden state
  output, hidden = self.rnn(input, h0)
  output = output[:, -1, :] # 只使用最终时刻的输出作为特征
  output = self.liner(output)
  output = F.softmax(output, dim=1)
  return output

hidden_dim = 128
output_dim = 2

class Model:
 def __init__(self, epoches=100):
  self.model = CharRNN(len(chars), hidden_dim , output_dim)
  self.model.to(device)
  self.epoches = epoches

 def train(self, train_set):
  loss_func = nn.CrossEntropyLoss()
  optimizer = torch.optim.RMSprop(self.model.parameters(), lr=0.0003)

  for epoch in range(self.epoches):
   total_loss = 0
   for x in range(1000):# 每轮随机样本训练1000次
    name, sexy = random.choice(train_set)
    # RNN的input要求shape为[batch, seq_len, embed_dim]，由于名字为变长，也不准备好将其填充为定长，因此batch_size取1，将取的名字放入单个元素的list中。
    name_tensor = torch.tensor([name], dtype=torch.float, device=device)
    # torch要求计算损失时，只提供类别的索引值，不需要one-hot表示
    sexy_tensor = torch.tensor([sexy], dtype=torch.long, device=device)

    optimizer.zero_grad()

    pred = self.model(name_tensor) # [batch, out_dim]
    loss = loss_func(pred, sexy_tensor)
    loss.backward()
    total_loss += loss
    optimizer.step()
   print("Training: in epoch {} loss {}".format(epoch, total_loss/1000))

 def evaluate(self, test_set):
  with torch.no_grad(): # 评估时不进行梯度计算
   correct = 0
   for x in range(1000): # 从测试集中随机采样测试1000次
    name, sexy = random.choice(test_set)
    name_tensor = torch.tensor([name], dtype=torch.float, device=device)

    pred = self.model(name_tensor)
    if torch.argmax(pred).item() == sexy:
     correct += 1

   print('Evaluating: test accuracy is {}%'.format(correct/10.0))

 def predict(self, name):
  p = name2vec(name.lower())
  name_tensor = torch.tensor([p], dtype=torch.float, device=device)
  with torch.no_grad():
   out = self.model(name_tensor)
   out = torch.argmax(out).item()
   sexy = 'female' if out == 0 else 'male'
   print('{} is {}'.format(name, sexy))


if __name__ == "__main__":
 model = Model(10)
 data_set = load_data()
 train, test = sklearn.model_selection.train_test_split(data_set)
 model.train(train)
 model.evaluate(test)
 model.predict("Jim")
 model.predict('Kate')
'''
Evaluating: test accuracy is 82.6%
Jim is male
Kate is female
'''

# coding=utf-8
import torch
from torch import nn
import torch.nn.functional as F
import numpy as np
import string
import random
import nltk
nltk.download('names')
from nltk.corpus import names

USE_CUDA = torch.cuda.is_available()
device = torch.device("cuda" if USE_CUDA else "cpu")

# 使用符号!作为名字的结束标识
chars = string.ascii_lowercase + '-' + ' ' + "'" + '!'

hidden_dim = 128
output_dim = len(chars)

# name abc encode as [[1, ...], [0,1,...], [0,0,1...]]
def name2input(name):
 ids = [chars.index(c) for c in name if c not in ["\\"]]
 a = np.zeros(shape=(len(ids), len(chars)), dtype=np.long)
 for i, idx in enumerate(ids):
  a[i][idx] = 1
 return a

# name abc encode as [0 1 2]
def name2target(name):
 ids = [chars.index(c) for c in name if c not in ["\\"]]
 return ids

# female=[[1, 0]] male=[[0,1]]
def sexy2input(sexy):
 a = np.zeros(shape=(1, 2), dtype=np.long)
 a[0][sexy] = 1
 return a


def load_data():
 female_file, male_file = names.fileids()

 f1_names = names.words(female_file)
 f2_names = names.words(male_file)

 data_set = [(name.lower(), 0) for name in f1_names] + [(name.lower(), 1) for name in f2_names]
 random.shuffle(data_set)
 print(data_set[:10])
 return data_set

'''
[('yoshiko', 0), ('timothea', 0), ('giorgi', 1), ('thedrick', 1), ('tessie', 0), ('keith', 1), ('carena', 0), ('anthea', 0), ('cathyleen', 0), ('almeta', 0)]
'''
class CharRNN(nn.Module):
 def __init__(self, vocab_size, hidden_size, output_size):
  super(CharRNN, self).__init__()
  self.vocab_size = vocab_size
  self.hidden_size = hidden_size
  self.output_size = output_size
  # 输入维度增加了性别的one-hot嵌入，dim+=2
  self.rnn = nn.GRU(vocab_size+2, hidden_size, batch_first=True)
  self.liner = nn.Linear(hidden_size, output_size)

 def forward(self, sexy, name, hidden=None):
  if hidden is None:
   hidden = torch.zeros(1, 1, self.hidden_size, device=device) # 初始hidden state
  # 对每个输入字符，将性别向量嵌入到头部
  input = torch.cat([sexy, name], dim=2)
  output, hidden = self.rnn(input, hidden)
  output = self.liner(output)
  output = F.dropout(output, 0.3)
  output = F.softmax(output, dim=2)
  return output.view(1, -1), hidden


class Model:
 def __init__(self, epoches):
  self.model = CharRNN(len(chars), hidden_dim , output_dim)
  self.model.to(device)
  self.epoches = epoches

 def train(self, train_set):
  loss_func = nn.CrossEntropyLoss()
  optimizer = torch.optim.RMSprop(self.model.parameters(), lr=0.001)

  for epoch in range(self.epoches):
   total_loss = 0
   for x in range(1000): # 每轮随机样本训练1000次
    loss = 0
    name, sexy = random.choice(train_set)
    optimizer.zero_grad()
    hidden = torch.zeros(1, 1, hidden_dim, device=device)
    # 对于姓名kate，将kate作为输入，ate!作为训输出，依次将每个字符输入网络，以计算误差
    for x, y in zip(list(name), list(name[1:]+'!')):
     name_tensor = torch.tensor([name2input(x)], dtype=torch.float, device=device)
     sexy_tensor = torch.tensor([sexy2input(sexy)], dtype=torch.float, device=device)
     target_tensor = torch.tensor(name2target(y), dtype=torch.long, device=device)

     pred, hidden = self.model(sexy_tensor, name_tensor, hidden)
     loss += loss_func(pred, target_tensor)

    loss.backward()
    optimizer.step()

    total_loss += loss/(len(name) - 1)

   print("Training: in epoch {} loss {}".format(epoch, total_loss/1000))

 def sample(self, sexy, start):
  max_len = 8
  result = []
  with torch.no_grad():
   hidden = None
   for c in start:
    sexy_tensor = torch.tensor([sexy2input(sexy)], dtype=torch.float, device=device)
    name_tensor = torch.tensor([name2input(c)], dtype=torch.float, device=device)
    pred, hidden = self.model(sexy_tensor, name_tensor, hidden)

   c = start[-1]
   while c != '!':
    sexy_tensor = torch.tensor([sexy2input(sexy)], dtype=torch.float, device=device)
    name_tensor = torch.tensor([name2input(c)], dtype=torch.float, device=device)
    pred, hidden = self.model(sexy_tensor, name_tensor, hidden)
    topv, topi = pred.topk(1)
    c = chars[topi]

    # c = chars[torch.argmax(pred)]
    result.append(c)

    if len(result) > max_len:
     break

  return start + "".join(result[:-1])


if __name__ == "__main__":
 model = Model(10)
 data_set = load_data()

 model.train(data_set)
 print(model.sample(0, "ka"))
 c = input('please input name prefix: ')
 while c != 'q':
  print(model.sample(1, c))
  print(model.sample(0, c))
  c = input('please input name prefix: ')