dilated convolutions
发布时间
阅读量：
阅读量
# encoding = utf-8
import numpy as np
import tensorflow as tf
from tensorflow.contrib.crf import crf_log_likelihood
from tensorflow.contrib.crf import viterbi_decode
from tensorflow.contrib.layers.python.layers import initializers
from utils import result_to_json
from data_utils import create_input, iobes_iob,iob_iobes
class Model(object):
#初始化模型参数
def __init__(self, config):
self.config = config
self.lr = config["lr"]
self.char_dim = config["char_dim"]
self.lstm_dim = config["lstm_dim"]
self.seg_dim = config["seg_dim"]
self.num_tags = config["num_tags"]
self.num_chars = config["num_chars"]#样本中总字数
self.num_segs = 4
self.global_step = tf.Variable(0, trainable=False)
self.best_dev_f1 = tf.Variable(0.0, trainable=False)
self.best_test_f1 = tf.Variable(0.0, trainable=False)
self.initializer = initializers.xavier_initializer()
# add placeholders for the model
self.char_inputs = tf.placeholder(dtype=tf.int32,
shape=[None, None],
name="ChatInputs")
self.seg_inputs = tf.placeholder(dtype=tf.int32,
shape=[None, None],
name="SegInputs")
self.targets = tf.placeholder(dtype=tf.int32,
shape=[None, None],
name="Targets")
# dropout keep prob
self.dropout = tf.placeholder(dtype=tf.float32,
name="Dropout")
used = tf.sign(tf.abs(self.char_inputs))
length = tf.reduce_sum(used, reduction_indices=1)
self.lengths = tf.cast(length, tf.int32)
self.batch_size = tf.shape(self.char_inputs)[0]
self.num_steps = tf.shape(self.char_inputs)[-1]
#Add model type by crownpku bilstm or idcnn
self.model_type = config['model_type']
#parameters for idcnn
self.layers = [
{
'dilation': 1
},
{
'dilation': 1
},
{
'dilation': 2
},
]
self.filter_width = 3
self.num_filter = self.lstm_dim
self.embedding_dim = self.char_dim + self.seg_dim
self.repeat_times = 4
self.cnn_output_width = 0
# embeddings for chinese character and segmentation representation
embedding = self.embedding_layer(self.char_inputs, self.seg_inputs, config)
if self.model_type == 'bilstm':
# apply dropout before feed to lstm layer
model_inputs = tf.nn.dropout(embedding, self.dropout)
# bi-directional lstm layer
model_outputs = self.biLSTM_layer(model_inputs, self.lstm_dim, self.lengths)
# logits for tags
self.logits = self.project_layer_bilstm(model_outputs)
elif self.model_type == 'idcnn':
# apply dropout before feed to idcnn layer
model_inputs = tf.nn.dropout(embedding, self.dropout)
# ldcnn layer
model_outputs = self.IDCNN_layer(model_inputs)
# logits for tags
self.logits = self.project_layer_idcnn(model_outputs)
else:
raise KeyError
# loss of the model
self.loss = self.loss_layer(self.logits, self.lengths)
with tf.variable_scope("optimizer"):
optimizer = self.config["optimizer"]
if optimizer == "sgd":
self.opt = tf.train.GradientDescentOptimizer(self.lr)
elif optimizer == "adam":
self.opt = tf.train.AdamOptimizer(self.lr)
elif optimizer == "adgrad":
self.opt = tf.train.AdagradOptimizer(self.lr)
else:
raise KeyError
# apply grad clip to avoid gradient explosion
grads_vars = self.opt.compute_gradients(self.loss)
capped_grads_vars = [[tf.clip_by_value(g, -self.config["clip"], self.config["clip"]), v]
for g, v in grads_vars] #config["clip"]梯度截断【-5,5】范围内
self.train_op = self.opt.apply_gradients(capped_grads_vars, self.global_step)
# saver of the model
self.saver = tf.train.Saver(tf.global_variables(), max_to_keep=5)
def embedding_layer(self, char_inputs, seg_inputs, config, name=None):
"""
:param char_inputs: one-hot encoding of sentence
:param seg_inputs: segmentation feature
:param config: wither use segmentation feature
:return: [1, num_steps, embedding size],
"""
#高:3 血:22 糖:23 和:24 高:3 血:22 压:25 char_inputs=[3,22,23,24,3,22,25]
#高血糖 和 高血压 seg_inputs 高血糖=[1,2,3] 和=[0] 高血压=[1,2,3] seg_inputs=[1,2,3,0,1,2,3]
embedding = []
self.char_inputs_test=char_inputs
self.seg_inputs_test=seg_inputs
with tf.variable_scope("char_embedding" if not name else name), tf.device('/cpu:0'):
self.char_lookup = tf.get_variable(
name="char_embedding",
shape=[self.num_chars, self.char_dim],
initializer=self.initializer)
#输入char_inputs='常' 对应的字典的索引/编号/value为：8
#self.char_lookup=[2677*100]的向量，char_inputs字对应在字典的索引/编号/key=[1]
embedding.append(tf.nn.embedding_lookup(self.char_lookup, char_inputs))
#self.embedding1.append(tf.nn.embedding_lookup(self.char_lookup, char_inputs))
if config["seg_dim"]:
with tf.variable_scope("seg_embedding"), tf.device('/cpu:0'):
self.seg_lookup = tf.get_variable(
name="seg_embedding",
#shape=[4*20]
shape=[self.num_segs, self.seg_dim],
initializer=self.initializer)
embedding.append(tf.nn.embedding_lookup(self.seg_lookup, seg_inputs))
embed = tf.concat(embedding, axis=-1)
self.embed_test=embed
self.embedding_test=embedding
return embed
def biLSTM_layer(self, model_inputs, lstm_dim, lengths, name=None):
"""
:param lstm_inputs: [batch_size, num_steps, emb_size]
:return: [batch_size, num_steps, 2*lstm_dim]
"""
with tf.variable_scope("char_BiLSTM" if not name else name):
lstm_cell = {}
for direction in ["forward", "backward"]:
with tf.variable_scope(direction):
lstm_cell[direction] = tf.contrib.rnn.CoupledInputForgetGateLSTMCell(
lstm_dim,
use_peepholes=True,
initializer=self.initializer,
state_is_tuple=True)
outputs, final_states = tf.nn.bidirectional_dynamic_rnn(
lstm_cell["forward"],
lstm_cell["backward"],
model_inputs,
dtype=tf.float32,
sequence_length=lengths)
return tf.concat(outputs, axis=2)
#IDCNN layer
def IDCNN_layer(self, model_inputs,
name=None):
"""
:param idcnn_inputs: [batch_size, num_steps, emb_size]
:return: [batch_size, num_steps, cnn_output_width]
"""
#tf.expand_dims会向tensor中插入一个维度，插入位置就是参数代表的位置（维度从0开始）。
model_inputs = tf.expand_dims(model_inputs, 1)
self.model_inputs_test=model_inputs
reuse = False
if self.dropout == 1.0:
reuse = True
with tf.variable_scope("idcnn" if not name else name):
#shape=[1*3*120*100]
# shape=[1, self.filter_width, self.embedding_dim,
# self.num_filter]
# print(shape)
filter_weights = tf.get_variable(
"idcnn_filter",
shape=[1, self.filter_width, self.embedding_dim,
self.num_filter],
initializer=self.initializer)
"""
shape of input = [batch, in_height, in_width, in_channels]
shape of filter = [filter_height, filter_width, in_channels, out_channels]
"""
layerInput = tf.nn.conv2d(model_inputs,
filter_weights,
strides=[1, 1, 1, 1],
padding="SAME",
name="init_layer",use_cudnn_on_gpu=False)
self.layerInput_test=layerInput
finalOutFromLayers = []
totalWidthForLastDim = 0
for j in range(self.repeat_times):
for i in range(len(self.layers)):
#1,1,2
dilation = self.layers[i]['dilation']
isLast = True if i == (len(self.layers) - 1) else False
with tf.variable_scope("atrous-conv-layer-%d" % i,
reuse=True
if (reuse or j > 0) else False):
#w 卷积核的高度，卷积核的宽度，图像通道数，卷积核个数
w = tf.get_variable(
"filterW",
shape=[1, self.filter_width, self.num_filter,
self.num_filter],
initializer=tf.contrib.layers.xavier_initializer())
if j==1 and i==1:
self.w_test_1=w
if j==2 and i==1:
self.w_test_2=w
b = tf.get_variable("filterB", shape=[self.num_filter])
#tf.nn.atrous_conv2d(value,filters,rate,padding,name=None）
#除去name参数用以指定该操作的name，与方法有关的一共四个参数：
#value：
#指需要做卷积的输入图像，要求是一个4维Tensor，具有[batch, height, width, channels]这样的shape，具体含义是[训练时一个batch的图片数量, 图片高度, 图片宽度, 图像通道数]
#filters：
#相当于CNN中的卷积核，要求是一个4维Tensor，具有[filter_height, filter_width, channels, out_channels]这样的shape，具体含义是[卷积核的高度，卷积核的宽度，图像通道数，卷积核个数]，同理这里第三维channels，就是参数value的第四维
#rate：
#要求是一个int型的正数，正常的卷积操作应该会有stride（即卷积核的滑动步长），但是空洞卷积是没有stride参数的，
#这一点尤其要注意。取而代之，它使用了新的rate参数，那么rate参数有什么用呢？它定义为我们在输入
#图像上卷积时的采样间隔，你可以理解为卷积核当中穿插了（rate-1）数量的“0”，
#把原来的卷积核插出了很多“洞洞”，这样做卷积时就相当于对原图像的采样间隔变大了。
#具体怎么插得，可以看后面更加详细的描述。此时我们很容易得出rate=1时，就没有0插入，
#此时这个函数就变成了普通卷积。
#padding：
#string类型的量，只能是”SAME”,”VALID”其中之一，这个值决定了不同边缘填充方式。
#ok，完了，到这就没有参数了，或许有的小伙伴会问那“stride”参数呢。其实这个函数已经默认了stride=1，也就是滑动步长无法改变，固定为1。
#结果返回一个Tensor，填充方式为“VALID”时，返回[batch,height-2*(filter_width-1),width-2*(filter_height-1),out_channels]的Tensor，填充方式为“SAME”时，返回[batch, height, width, out_channels]的Tensor，这个结果怎么得出来的？先不急，我们通过一段程序形象的演示一下空洞卷积。
conv = tf.nn.atrous_conv2d(layerInput,
w,
rate=dilation,
padding="SAME")
self.conv_test=conv
conv = tf.nn.bias_add(conv, b)
conv = tf.nn.relu(conv)
if isLast:
finalOutFromLayers.append(conv)
totalWidthForLastDim += self.num_filter
layerInput = conv
finalOut = tf.concat(axis=3, values=finalOutFromLayers)
keepProb = 1.0 if reuse else 0.5
finalOut = tf.nn.dropout(finalOut, keepProb)
#Removes dimensions of size 1 from the shape of a tensor.
#从tensor中删除所有大小是1的维度
#Given a tensor input, this operation returns a tensor of the same type with all dimensions of size 1 removed. If you don’t want to remove all size 1 dimensions, you can remove specific size 1 dimensions by specifying squeeze_dims.
#给定张量输入，此操作返回相同类型的张量，并删除所有尺寸为1的尺寸。 如果不想删除所有尺寸1尺寸，可以通过指定squeeze_dims来删除特定尺寸1尺寸。
finalOut = tf.squeeze(finalOut, [1])
finalOut = tf.reshape(finalOut, [-1, totalWidthForLastDim])
self.cnn_output_width = totalWidthForLastDim
return finalOut
def project_layer_bilstm(self, lstm_outputs, name=None):
"""
hidden layer between lstm layer and logits
:param lstm_outputs: [batch_size, num_steps, emb_size]
:return: [batch_size, num_steps, num_tags]
"""
with tf.variable_scope("project" if not name else name):
with tf.variable_scope("hidden"):
W = tf.get_variable("W", shape=[self.lstm_dim*2, self.lstm_dim],
dtype=tf.float32, initializer=self.initializer)
b = tf.get_variable("b", shape=[self.lstm_dim], dtype=tf.float32,
initializer=tf.zeros_initializer())
output = tf.reshape(lstm_outputs, shape=[-1, self.lstm_dim*2])
hidden = tf.tanh(tf.nn.xw_plus_b(output, W, b))
# project to score of tags
with tf.variable_scope("logits"):
W = tf.get_variable("W", shape=[self.lstm_dim, self.num_tags],
dtype=tf.float32, initializer=self.initializer)
b = tf.get_variable("b", shape=[self.num_tags], dtype=tf.float32,
initializer=tf.zeros_initializer())
pred = tf.nn.xw_plus_b(hidden, W, b)
return tf.reshape(pred, [-1, self.num_steps, self.num_tags])
#Project layer for idcnn by crownpku
#Delete the hidden layer, and change bias initializer
def project_layer_idcnn(self, idcnn_outputs, name=None):
"""
:param lstm_outputs: [batch_size, num_steps, emb_size]
:return: [batch_size, num_steps, num_tags]
"""
with tf.variable_scope("project" if not name else name):
# project to score of tags
with tf.variable_scope("logits"):
W = tf.get_variable("W", shape=[self.cnn_output_width, self.num_tags],
dtype=tf.float32, initializer=self.initializer)
b = tf.get_variable("b", initializer=tf.constant(0.001, shape=[self.num_tags]))
pred = tf.nn.xw_plus_b(idcnn_outputs, W, b)
return tf.reshape(pred, [-1, self.num_steps, self.num_tags])
def loss_layer(self, project_logits, lengths, name=None):
"""
calculate crf loss
:param project_logits: [1, num_steps, num_tags]
:return: scalar loss
"""
with tf.variable_scope("crf_loss" if not name else name):
small = -1000.0
# pad logits for crf loss
start_logits = tf.concat(
[small * tf.ones(shape=[self.batch_size, 1, self.num_tags]), tf.zeros(shape=[self.batch_size, 1, 1])], axis=-1)
pad_logits = tf.cast(small * tf.ones([self.batch_size, self.num_steps, 1]), tf.float32)
logits = tf.concat([project_logits, pad_logits], axis=-1)
logits = tf.concat([start_logits, logits], axis=1)
targets = tf.concat(
[tf.cast(self.num_tags*tf.ones([self.batch_size, 1]), tf.int32), self.targets], axis=-1)
self.trans = tf.get_variable(
"transitions",
shape=[self.num_tags + 1, self.num_tags + 1],
initializer=self.initializer)
#crf_log_likelihood在一个条件随机场里面计算标签序列的log-likelihood
#inputs: 一个形状为[batch_size, max_seq_len, num_tags] 的tensor,
#一般使用BILSTM处理之后输出转换为他要求的形状作为CRF层的输入.
#tag_indices: 一个形状为[batch_size, max_seq_len] 的矩阵,其实就是真实标签.
#sequence_lengths: 一个形状为 [batch_size] 的向量,表示每个序列的长度.
#transition_params: 形状为[num_tags, num_tags] 的转移矩阵
#log_likelihood: 标量,log-likelihood
#transition_params: 形状为[num_tags, num_tags] 的转移矩阵
log_likelihood, self.trans = crf_log_likelihood(
inputs=logits,
tag_indices=targets,
transition_params=self.trans,
sequence_lengths=lengths+1)
return tf.reduce_mean(-log_likelihood)
def create_feed_dict(self, is_train, batch):
"""
:param is_train: Flag, True for train batch
:param batch: list train/evaluate data
:return: structured data to feed
"""
_, chars, segs, tags = batch
feed_dict = {
self.char_inputs: np.asarray(chars),
self.seg_inputs: np.asarray(segs),
self.dropout: 1.0,
}
if is_train:
feed_dict[self.targets] = np.asarray(tags)
feed_dict[self.dropout] = self.config["dropout_keep"]
return feed_dict
def run_step(self, sess, is_train, batch):
"""
:param sess: session to run the batch
:param is_train: a flag indicate if it is a train batch
:param batch: a dict containing batch data
:return: batch result, loss of the batch or logits
"""
feed_dict = self.create_feed_dict(is_train, batch)
if is_train:
global_step, loss,_,char_lookup_out,seg_lookup_out,char_inputs_test,seg_inputs_test,embed_test,embedding_test,\
model_inputs_test,layerInput_test,conv_test,w_test_1,w_test_2,char_inputs_test= sess.run(
[self.global_step, self.loss, self.train_op,self.char_lookup,self.seg_lookup,self.char_inputs_test,self.seg_inputs_test,\
self.embed_test,self.embedding_test,self.model_inputs_test,self.layerInput_test,self.conv_test,self.w_test_1,self.w_test_2,self.char_inputs],
feed_dict)
return global_step, loss
else:
lengths, logits = sess.run([self.lengths, self.logits], feed_dict)
return lengths, logits
def decode(self, logits, lengths, matrix):
"""
:param logits: [batch_size, num_steps, num_tags]float32, logits
:param lengths: [batch_size]int32, real length of each sequence
:param matrix: transaction matrix for inference
:return:
"""
# inference final labels usa viterbi Algorithm
paths = []
small = -1000.0
start = np.asarray([[small]*self.num_tags +[0]])
for score, length in zip(logits, lengths):
score = score[:length]
pad = small * np.ones([length, 1])
logits = np.concatenate([score, pad], axis=1)
logits = np.concatenate([start, logits], axis=0)
path, _ = viterbi_decode(logits, matrix)
paths.append(path[1:])
return paths
def evaluate(self, sess, data_manager, id_to_tag):
"""
:param sess: session to run the model
:param data: list of data
:param id_to_tag: index to tag name
:return: evaluate result
"""
results = []
trans = self.trans.eval()
for batch in data_manager.iter_batch():
strings = batch[0]
tags = batch[-1]
lengths, scores = self.run_step(sess, False, batch)
batch_paths = self.decode(scores, lengths, trans)
for i in range(len(strings)):
result = []
string = strings[i][:lengths[i]]
gold = iobes_iob([id_to_tag[int(x)] for x in tags[i][:lengths[i]]])
pred = iobes_iob([id_to_tag[int(x)] for x in batch_paths[i][:lengths[i]]])
#gold = iob_iobes([id_to_tag[int(x)] for x in tags[i][:lengths[i]]])
#pred = iob_iobes([id_to_tag[int(x)] for x in batch_paths[i][:lengths[i]]])
for char, gold, pred in zip(string, gold, pred):
result.append(" ".join([char, gold, pred]))
results.append(result)
return results
def evaluate_line(self, sess, inputs, id_to_tag):
trans = self.trans.eval(session=sess)
lengths, scores = self.run_step(sess, False, inputs)
batch_paths = self.decode(scores, lengths, trans)
tags = [id_to_tag[idx] for idx in batch_paths[0]]
return result_to_json(inputs[0][0], tags)
代码解读 # encoding=utf8
import pickle
import itertools
from collections import OrderedDict
import os
import tensorflow as tf
import numpy as np
from model import Model
from loader import load_sentences, update_tag_scheme
from loader import char_mapping, tag_mapping
from loader import augment_with_pretrained, prepare_dataset
from utils import get_logger, make_path, clean, create_model, save_model
from utils import print_config, save_config, load_config, test_ner
from data_utils import load_word2vec, create_input, input_from_line, BatchManager
root_path=os.getcwd()+os.sep
flags = tf.app.flags
flags.DEFINE_boolean("clean", True, "clean train folder")
flags.DEFINE_boolean("train", False, "Whether train the model")
# configurations for the model
flags.DEFINE_integer("seg_dim", 20, "Embedding size for segmentation, 0 if not used")
flags.DEFINE_integer("char_dim", 100, "Embedding size for characters")
flags.DEFINE_integer("lstm_dim", 100, "Num of hidden units in LSTM, or num of filters in IDCNN")
flags.DEFINE_string("tag_schema", "iobes", "tagging schema iobes or iob")
# configurations for training
flags.DEFINE_float("clip", 5, "Gradient clip")
flags.DEFINE_float("dropout", 0.5, "Dropout rate")
flags.DEFINE_float("batch_size", 60, "batch size")
flags.DEFINE_float("lr", 0.001, "Initial learning rate")
flags.DEFINE_string("optimizer", "adam", "Optimizer for training")
flags.DEFINE_boolean("pre_emb", True, "Wither use pre-trained embedding")
flags.DEFINE_boolean("zeros", True, "Wither replace digits with zero")
flags.DEFINE_boolean("lower", False, "Wither lower case")
flags.DEFINE_integer("max_epoch", 100, "maximum training epochs")
flags.DEFINE_integer("steps_check", 100, "steps per checkpoint")
flags.DEFINE_string("ckpt_path", "ckpt", "Path to save model")
flags.DEFINE_string("summary_path", "summary", "Path to store summaries")
flags.DEFINE_string("log_file", "train.log", "File for log")
flags.DEFINE_string("map_file", "./config/maps.pkl", "file for maps")
flags.DEFINE_string("vocab_file", "vocab.json", "File for vocab")
flags.DEFINE_string("config_file", "./config/config_file", "File for config")
flags.DEFINE_string("tag_to_id_path", "./config/tag_to_id.txt", "File for tag_to_id.txt")
flags.DEFINE_string("id_to_tag_path", "./config/id_to_tag.txt", "File for id_to_tag.txt")
flags.DEFINE_string("script", "conlleval", "evaluation script")
flags.DEFINE_string("result_path", "result", "Path for results")
flags.DEFINE_string("emb_file", os.path.join(root_path+"data", "vec.txt"), "Path for pre_trained embedding")
flags.DEFINE_string("train_file", os.path.join(root_path+"data", "example.dev"), "Path for train data") # example.train
flags.DEFINE_string("dev_file", os.path.join(root_path+"data", "example.dev"), "Path for dev data") # 注意，这里的数据集我都做了修改，为了在我的机器上运行
flags.DEFINE_string("test_file", os.path.join(root_path+"data", "example.dev"), "Path for test data") # example.test
flags.DEFINE_string("model_type", "idcnn", "Model type, can be idcnn or bilstm")
#flags.DEFINE_string("model_type", "bilstm", "Model type, can be idcnn or bilstm")
FLAGS = tf.app.flags.FLAGS
assert FLAGS.clip < 5.1, "gradient clip should't be too much"
assert 0 <= FLAGS.dropout < 1, "dropout rate between 0 and 1"
assert FLAGS.lr > 0, "learning rate must larger than zero"
assert FLAGS.optimizer in ["adam", "sgd", "adagrad"]
# config for the model
def config_model(char_to_id, tag_to_id):
config = OrderedDict()
config["model_type"] = FLAGS.model_type
config["num_chars"] = len(char_to_id)
config["char_dim"] = FLAGS.char_dim
config["num_tags"] = len(tag_to_id)
config["seg_dim"] = FLAGS.seg_dim
config["lstm_dim"] = FLAGS.lstm_dim
config["batch_size"] = FLAGS.batch_size
config["emb_file"] = FLAGS.emb_file
config["clip"] = FLAGS.clip
config["dropout_keep"] = 1.0 - FLAGS.dropout
config["optimizer"] = FLAGS.optimizer
config["lr"] = FLAGS.lr
config["tag_schema"] = FLAGS.tag_schema
config["pre_emb"] = FLAGS.pre_emb
config["zeros"] = FLAGS.zeros
config["lower"] = FLAGS.lower
return config
def evaluate(sess, model, name, data, id_to_tag, logger):
logger.info("evaluate:{}".format(name))
ner_results = model.evaluate(sess, data, id_to_tag)
eval_lines = test_ner(ner_results, FLAGS.result_path)
for line in eval_lines:
logger.info(line)
f1 = float(eval_lines[1].strip().split()[-1])
if name == "dev":
best_test_f1 = model.best_dev_f1.eval()
if f1 > best_test_f1:
tf.assign(model.best_dev_f1, f1).eval()
logger.info("new best dev f1 score:{:>.3f}".format(f1))
return f1 > best_test_f1
elif name == "test":
best_test_f1 = model.best_test_f1.eval()
if f1 > best_test_f1:
tf.assign(model.best_test_f1, f1).eval()
logger.info("new best test f1 score:{:>.3f}".format(f1))
return f1 > best_test_f1
def train():
# load data sets
train_sentences = load_sentences(FLAGS.train_file, FLAGS.lower, FLAGS.zeros)
dev_sentences = load_sentences(FLAGS.dev_file, FLAGS.lower, FLAGS.zeros)
test_sentences = load_sentences(FLAGS.test_file, FLAGS.lower, FLAGS.zeros)
# Use selected tagging scheme (IOB / IOBES) I：中间，O：其他，B：开始 | E：结束，S：单个
update_tag_scheme(train_sentences, FLAGS.tag_schema)
update_tag_scheme(test_sentences, FLAGS.tag_schema)
update_tag_scheme(dev_sentences, FLAGS.tag_schema)
# create maps if not exist
if not os.path.isfile(FLAGS.map_file): # 配置文件：char_to_id, id_to_char, tag_to_id, id_to_tag的数据
# create dictionary for word
if FLAGS.pre_emb:
dico_chars_train = char_mapping(train_sentences, FLAGS.lower)[0]
dico_chars, char_to_id, id_to_char = augment_with_pretrained(
dico_chars_train.copy(),
FLAGS.emb_file,
list(itertools.chain.from_iterable(
[[w[0] for w in s] for s in test_sentences])
)
)
else:
_c, char_to_id, id_to_char = char_mapping(train_sentences, FLAGS.lower)
# Create a dictionary and a mapping for tags
_t, tag_to_id, id_to_tag = tag_mapping(train_sentences,FLAGS.id_to_tag_path,FLAGS.tag_to_id_path)
#with open('maps.txt','w',encoding='utf8') as f1:
#f1.writelines(str(char_to_id)+" "+id_to_char+" "+str(tag_to_id)+" "+id_to_tag+'\n')
with open(FLAGS.map_file, "wb") as f:
pickle.dump([char_to_id, id_to_char, tag_to_id, id_to_tag], f)
else:
with open(FLAGS.map_file, "rb") as f:
char_to_id, id_to_char, tag_to_id, id_to_tag = pickle.load(f) #
# prepare data, get a collection of list containing index
train_data = prepare_dataset( # train_data[0][0]:一句话；train_data[0][1]：单个字的编号；train_data[0][2]：切词之后，切词特征：词的大小是一个字的话是0，词的大小是2以上的话：1,2.。。，2,3； train_data[0][3]：每个字的标签
train_sentences, char_to_id, tag_to_id, FLAGS.lower
)
dev_data = prepare_dataset(
dev_sentences, char_to_id, tag_to_id, FLAGS.lower
)
test_data = prepare_dataset(
test_sentences, char_to_id, tag_to_id, FLAGS.lower
)
print("%i / %i / %i sentences in train / dev / test." % (
len(train_data), 0, len(test_data)))
train_manager = BatchManager(train_data, FLAGS.batch_size) # 将数据拆分成以60句话为一个batch
dev_manager = BatchManager(dev_data, 100)
test_manager = BatchManager(test_data, 100)
# make path for store log and model if not exist
make_path(FLAGS)
if os.path.isfile(FLAGS.config_file):
config = load_config(FLAGS.config_file)
else:
config = config_model(char_to_id, tag_to_id)
save_config(config, FLAGS.config_file)
make_path(FLAGS)
log_path = os.path.join("log", FLAGS.log_file)
logger = get_logger(log_path)
print_config(config, logger)
# limit GPU memory
tf_config = tf.ConfigProto()
tf_config.gpu_options.allow_growth = True
steps_per_epoch = train_manager.len_data
with tf.Session(config=tf_config) as sess:
model = create_model(sess, Model, FLAGS.ckpt_path, load_word2vec, config, id_to_char, logger)
logger.info("start training")
loss = []
with tf.device("/cpu:0"):
for i in range(100):
for batch in train_manager.iter_batch(shuffle=True):
step, batch_loss = model.run_step(sess, True, batch) # 按批次训练模型 这个是训练的开始，可以从这里倒着找整个网络怎么训练
loss.append(batch_loss)
if step % FLAGS.steps_check == 0:
iteration = step // steps_per_epoch + 1
logger.info("iteration:{} step:{}/{}, "
"NER loss:{:>9.6f}".format(
iteration, step%steps_per_epoch, steps_per_epoch, np.mean(loss)))
loss = []
# best = evaluate(sess, model, "dev", dev_manager, id_to_tag, logger)
if i%7==0:
save_model(sess, model, FLAGS.ckpt_path, logger)
#evaluate(sess, model, "test", test_manager, id_to_tag, logger)
def evaluate_line():
config = load_config(FLAGS.config_file)
logger = get_logger(FLAGS.log_file)
# limit GPU memory
tf_config = tf.ConfigProto()
tf_config.gpu_options.allow_growth = True
with open(FLAGS.map_file, "rb") as f:
char_to_id, id_to_char, tag_to_id, id_to_tag = pickle.load(f)
with tf.Session(config=tf_config) as sess:
model = create_model(sess, Model, FLAGS.ckpt_path, load_word2vec, config, id_to_char, logger)
while True:
# try:
# line = input("请输入测试句子:")
# result = model.evaluate_line(sess, input_from_line(line, char_to_id), id_to_tag)
# print(result)
# except Exception as e:
# logger.info(e)
line = input("请输入测试句子:")
result = model.evaluate_line(sess, input_from_line(line, char_to_id), id_to_tag)
print(result)
def main(is_train):
if is_train:
if FLAGS.clean:
clean(FLAGS)
train() # 训练模式
else:
evaluate_line() # 测试模式
if __name__ == "__main__":
is_train = True
tf.app.run(main(is_train))
代码解读全部评论 (0)
还没有任何评论哟~