pytorch+lstm实现的pos示例-创新互联

学了几天终于大概明白pytorch怎么用了

这个是直接搬运的官方文档的代码

之后会自己试着实现其他nlp的任务

# Author: Robert Guthrie

import torch
import torch.autograd as autograd
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

torch.manual_seed(1)


lstm = nn.LSTM(3, 3) # Input dim is 3, output dim is 3
inputs = [autograd.Variable(torch.randn((1, 3)))
     for _ in range(5)] # make a sequence of length 5

# initialize the hidden state.
hidden = (autograd.Variable(torch.randn(1, 1, 3)),
     autograd.Variable(torch.randn((1, 1, 3))))
for i in inputs:
  # Step through the sequence one element at a time.
  # after each step, hidden contains the hidden state.
  out, hidden = lstm(i.view(1, 1, -1), hidden)

# alternatively, we can do the entire sequence all at once.
# the first value returned by LSTM is all of the hidden states throughout
# the sequence. the second is just the most recent hidden state
# (compare the last slice of "out" with "hidden" below, they are the same)
# The reason for this is that:
# "out" will give you access to all hidden states in the sequence
# "hidden" will allow you to continue the sequence and backpropagate,
# by passing it as an argument to the lstm at a later time
# Add the extra 2nd dimension
inputs = torch.cat(inputs).view(len(inputs), 1, -1)
hidden = (autograd.Variable(torch.randn(1, 1, 3)), autograd.Variable(
  torch.randn((1, 1, 3)))) # clean out hidden state
out, hidden = lstm(inputs, hidden)
#print(out)
#print(hidden)

#准备数据
def prepare_sequence(seq, to_ix):
  idxs = [to_ix[w] for w in seq]
  tensor = torch.LongTensor(idxs)
  return autograd.Variable(tensor)

training_data = [
  ("The dog ate the apple".split(), ["DET", "NN", "V", "DET", "NN"]),
  ("Everybody read that book".split(), ["NN", "V", "DET", "NN"])
]
word_to_ix = {}
for sent, tags in training_data:
  for word in sent:
    if word not in word_to_ix:
      word_to_ix[word] = len(word_to_ix)
print(word_to_ix)
tag_to_ix = {"DET": 0, "NN": 1, "V": 2}

# These will usually be more like 32 or 64 dimensional.
# We will keep them small, so we can see how the weights change as we train.
EMBEDDING_DIM = 6
HIDDEN_DIM = 6

#继承自nn.module
class LSTMTagger(nn.Module):

  def __init__(self, embedding_dim, hidden_dim, vocab_size, tagset_size):
    super(LSTMTagger, self).__init__()
    self.hidden_dim = hidden_dim

    #一个单词数量到embedding维数的矩阵
    self.word_embeddings = nn.Embedding(vocab_size, embedding_dim)

    #传入两个维度参数
    # The LSTM takes word embeddings as inputs, and outputs hidden states
    # with dimensionality hidden_dim.
    self.lstm = nn.LSTM(embedding_dim, hidden_dim)

    #线性layer从隐藏状态空间映射到tag便签
    # The linear layer that maps from hidden state space to tag space
    self.hidden2tag = nn.Linear(hidden_dim, tagset_size)
    self.hidden = self.init_hidden()

  def init_hidden(self):
    # Before we've done anything, we dont have any hidden state.
    # Refer to the Pytorch documentation to see exactly
    # why they have this dimensionality.
    # The axes semantics are (num_layers, minibatch_size, hidden_dim)
    return (autograd.Variable(torch.zeros(1, 1, self.hidden_dim)),
        autograd.Variable(torch.zeros(1, 1, self.hidden_dim)))

  def forward(self, sentence):
    embeds = self.word_embeddings(sentence)
    lstm_out, self.hidden = self.lstm(embeds.view(len(sentence), 1, -1), self.hidden)
    tag_space = self.hidden2tag(lstm_out.view(len(sentence), -1))
    tag_scores = F.log_softmax(tag_space)
    return tag_scores

#embedding维度，hidden维度，词语数量，标签数量
model = LSTMTagger(EMBEDDING_DIM, HIDDEN_DIM, len(word_to_ix), len(tag_to_ix))

#optim中存了各种优化算法
loss_function = nn.NLLLoss()
optimizer = optim.SGD(model.parameters(), lr=0.1)

# See what the scores are before training
# Note that element i,j of the output is the score for tag j for word i.
inputs = prepare_sequence(training_data[0][0], word_to_ix)
tag_scores = model(inputs)
print(tag_scores)

for epoch in range(300): # again, normally you would NOT do 300 epochs, it is toy data
  for sentence, tags in training_data:
    # Step 1. Remember that Pytorch accumulates gradients.
    # We need to clear them out before each instance
    model.zero_grad()

    # Also, we need to clear out the hidden state of the LSTM,
    # detaching it from its history on the last instance.
    model.hidden = model.init_hidden()

    # Step 2. Get our inputs ready for the network, that is, turn them into
    # Variables of word indices.
    sentence_in = prepare_sequence(sentence, word_to_ix)
    targets = prepare_sequence(tags, tag_to_ix)

    # Step 3. Run our forward pass.
    tag_scores = model(sentence_in)

    # Step 4. Compute the loss, gradients, and update the parameters by
    # calling optimizer.step()
    loss = loss_function(tag_scores, targets)
    loss.backward()
    optimizer.step()

# See what the scores are after training
inputs = prepare_sequence(training_data[0][0], word_to_ix)
tag_scores = model(inputs)
# The sentence is "the dog ate the apple". i,j corresponds to score for tag j
# for word i. The predicted tag is the maximum scoring tag.
# Here, we can see the predicted sequence below is 0 1 2 0 1
# since 0 is index of the maximum value of row 1,
# 1 is the index of maximum value of row 2, etc.
# Which is DET NOUN VERB DET NOUN, the correct sequence!
print(tag_scores)

另外有需要云服务器可以了解下创新互联scvps.cn，海内外云服务器15元起步，三天无理由+7*72小时售后在线，公司持有idc许可证，提供“云服务器、裸金属服务器、高防服务器、香港服务器、美国服务器、虚拟主机、免备案服务器”等云主机租用服务以及企业上云的综合解决方案，具有“安全稳定、简单易用、服务可用性高、性价比高”等特点与优势，专为企业上云打造定制，能够满足用户丰富、多元化的应用场景需求。