class XlnetEmbedding(BaseEmbedding):
def __init__(self, hyper_parameters):
self.layer_indexes = hyper_parameters['embedding'].get(
'layer_indexes', [24])
self.xlnet_embed = hyper_parameters['embedding'].get('xlnet_embed', {})
self.batch_size = hyper_parameters['model'].get('batch_size', 2)
super().__init__(hyper_parameters)
def build(self):
from keras_xlnet import load_trained_model_from_checkpoint, set_custom_objects
from keras_xlnet import Tokenizer, ATTENTION_TYPE_BI, ATTENTION_TYPE_UNI
self.embedding_type = 'xlnet'
self.checkpoint_path = os.path.join(self.corpus_path,
'xlnet_model.ckpt')
self.config_path = os.path.join(self.corpus_path, 'xlnet_config.json')
self.spiece_model = os.path.join(self.corpus_path, 'spiece.model')
self.attention_type = self.xlnet_embed.get('attention_type',
'bi') # or 'uni'
self.attention_type = ATTENTION_TYPE_BI if self.attention_type == 'bi' else ATTENTION_TYPE_UNI
self.memory_len = self.xlnet_embed.get('memory_len', 0)
self.target_len = self.xlnet_embed.get('target_len', 5)
print('load xlnet model start!')
# 模型加载
model = load_trained_model_from_checkpoint(
checkpoint_path=self.checkpoint_path,
attention_type=self.attention_type,
in_train_phase=self.trainable,
config_path=self.config_path,
memory_len=self.memory_len,
target_len=self.target_len,
batch_size=self.batch_size,
mask_index=0)
#
set_custom_objects()
# 字典加载
self.tokenizer = Tokenizer(self.spiece_model)
# debug时候查看layers
self.model_layers = model.layers
len_layers = self.model_layers.__len__()
print(len_layers)
layer_real = [i for i in range(25)] + [-i for i in range(25)]
# 简要判别一下
self.layer_indexes = [
i if i in layer_real else -2 for i in self.layer_indexes
]
len_couche = int((len_layers - 6) / 10)
# 一共246个layer
# 每层10个layer（MultiHeadAttention,Dropout,Add,LayerNormalization）,第一是9个layer的输入和embedding层
# 一共24层
layer_dict = []
layer_0 = 7
for i in range(len_couche):
layer_0 = layer_0 + 10
layer_dict.append(layer_0)
layer_dict.append(247)
# 测试 get_output_at
# def get_number(index):
# try:
# model_node = model.get_output_at(node_index=index)
# gg = 0
# except:
# print('node index wrong!')
# print(index)
# list_index = [i for i in range(25)] + [-i for i in range(25)]
# for li in list_index:
# get_number(li)
# 输出它本身
if len(self.layer_indexes) == 0:
encoder_layer = model.output
# 分类如果只有一层，取得不正确的话就取倒数第二层
elif len(self.layer_indexes) == 1:
if self.layer_indexes[0] in layer_real:
encoder_layer = model.get_layer(
index=layer_dict[self.layer_indexes[0]]).get_output_at(
node_index=0)
else:
encoder_layer = model.get_layer(
index=layer_dict[-1]).get_output_at(node_index=0)
# 否则遍历需要取的层，把所有层的weight取出来并加起来shape:768*层数
else:
# layer_indexes must be [0, 1, 2,3,......24]
all_layers = [
model.get_layer(index=layer_dict[lay]).get_output_at(
node_index=0) if lay in layer_real else model.get_layer(
index=layer_dict[-1]).get_output_at(
node_index=0) # 如果给出不正确，就默认输出倒数第一层
for lay in self.layer_indexes
]
print(self.layer_indexes)
print(all_layers)
all_layers_select = []
for all_layers_one in all_layers:
all_layers_select.append(all_layers_one)
encoder_layer = Add()(all_layers_select)
print(encoder_layer.shape)
# def xlnet_concat(x):
# x_concat = K.concatenate(x, axis=1)
# return x_concat
# encoder_layer = Lambda(xlnet_concat, name='xlnet_concat')(all_layers)
self.output = NonMaskingLayer()(encoder_layer)
self.input = model.inputs
self.model = Model(self.input, self.output)
print("load KerasXlnetEmbedding end")
model.summary(132)
self.embedding_size = self.model.output_shape[-1]
self.vocab_size = len(self.tokenizer.sp)
def sentence2idx(self, text, second_text=""):
# text = extract_chinese(str(text).upper())
text = str(text).upper()
tokens = self.tokenizer.encode(text)
tokens = tokens + [0] * (self.target_len - len(tokens)) \
if len(tokens) < self.target_len \
else tokens[0:self.target_len]
token_input = np.expand_dims(np.array(tokens), axis=0)
segment_input = np.zeros_like(token_input)
memory_length_input = np.zeros(
(1, 1)) # np.array([[self.memory_len]]) # np.zeros((1, 1))
masks = [1] * len(tokens) + ([0] * (self.target_len - len(tokens))
if len(tokens) < self.target_len else [])
mask_input = np.expand_dims(np.array(masks), axis=0)
if self.trainable:
return [
token_input, segment_input, memory_length_input, mask_input
]
else:
return [token_input, segment_input, memory_length_input]
import numpy as np
from keras_xlnet import PretrainedList, get_pretrained_paths
from keras_xlnet import Tokenizer, load_trained_model_from_checkpoint
from keras_xlnet import ATTENTION_TYPE_UNI, ATTENTION_TYPE_BI
checkpoint_path = "/home/xsq/nlp_code/sentiment_analysis/pretrain_model/chinese_xlnet_mid_L-24_H-768_A-12"
vocab_path = os.path.join(checkpoint_path, 'spiece.model')
config_path = os.path.join(checkpoint_path, 'xlnet_config.json')
model_path = os.path.join(checkpoint_path, 'xlnet_model.ckpt')
# Tokenize inputs
tokenizer = Tokenizer(vocab_path)
text = "这个苹果很好吃"
tokens = tokenizer.encode(text)
print(np.array(tokens).shape)
token_input = np.expand_dims(np.array(tokens), axis=0)
print(token_input.shape)
segment_input = np.zeros_like(token_input)
print(segment_input.shape)
memory_length_input = np.zeros((1, 1))
# Load pre-trained model
model = load_trained_model_from_checkpoint(
config_path=config_path,
checkpoint_path=model_path,
batch_size=1,
memory_len=0,
target_len=14,
class KerasXlnetVector:
def __init__(self, batch_size, gpu_name, gpu_num):
set_gpu_option(gpu_name, gpu_num)
self.attention_type = ATTENTION_TYPE_BI if args.attention_type[0] == 'bi' else ATTENTION_TYPE_UNI
self.memory_len, self.target_len, self.batch_size = args.memory_len, args.target_len, batch_size
self.checkpoint_path, self.config_path = args.ckpt_name, args.config_name
self.layer_indexes, self.in_train_phase = args.layer_indexes, False
print("##### load KerasXlnet start #####")
self.graph = tf.get_default_graph()
# 模型加载
self.model = load_trained_model_from_checkpoint(checkpoint_path=self.checkpoint_path,
attention_type=self.attention_type,
in_train_phase=self.in_train_phase,
config_path=self.config_path,
memory_len=self.memory_len,
target_len=self.target_len,
batch_size=self.batch_size,
mask_index=0)
# 字典加载
self.tokenizer = Tokenizer(args.spiece_model)
# debug时候查看layers
self.model_layers = self.model.layers
len_layers = self.model_layers.__len__()
len_couche = int((len_layers - 6) / 10)
# 一共126个layer
# 每层10个layer,第一是7个layer的输入和embedding层
# 一共12层
layer_dict = [5]
layer_0 = 6
for i in range(len_couche):
layer_0 = layer_0 + 10
layer_dict.append(layer_0 - 2)
# 输出它本身
if len(self.layer_indexes) == 0:
encoder_layer = self.model.output
# 分类如果只有一层，取得不正确的话就取倒数第二层
elif len(self.layer_indexes) == 1:
if self.layer_indexes[0] in [i + 1 for i in range(len_couche + 1)]:
encoder_layer = self.model.get_layer(index=layer_dict[self.layer_indexes[0]]).output
else:
encoder_layer = self.model.get_layer(index=layer_dict[-2]).output
# 否则遍历需要取的层，把所有层的weight取出来并加起来shape:768*层数
else:
# layer_indexes must be [0, 1, 2,3,......12]
all_layers = [self.model.get_layer(index=layer_dict[lay]).output
if lay in [i + 1 for i in range(len_couche + 1)]
else self.model.get_layer(index=layer_dict[-3]).output # 如果给出不正确，就默认输出倒数第二层
for lay in self.layer_indexes]
all_layers = all_layers[1:]
all_layers_select = []
for all_layers_one in all_layers:
all_layers_select.append(all_layers_one)
encoder_layer = Add()(all_layers_select)
output_layer = NonMaskingLayer()(encoder_layer)
model = Model(self.model.inputs, output_layer)
if gpu_num >= 2:
self.par_model = multi_gpu_model(model, gpus=gpu_num)
else:
self.par_model = model
print("##### load KerasXlnet end #####")
# model.summary()
def xlnet_encode(self, texts):
"""输入句子的列表，返回句向量列表"""
predicts = []
def create_array(): # 将输入的文本转换为词典序号的形式
data = []
for text in texts:
tokens = self.tokenizer.encode(text)
tokens = tokens + [0] * (self.target_len - len(tokens)) if len(tokens) < self.target_len else tokens[0:self.target_len] # padding
token_input = np.array(tokens)
mask_input = [0 if ids == 0 else 1 for ids in tokens].count(1)
segment_input = np.zeros_like(token_input)
memory_length_input = np.zeros(1)
data.append([token_input, mask_input, segment_input, memory_length_input])
return data
array = create_array()
my_iter = data_iter(array, batch_size=self.batch_size)
for w1, w2, w3, w4 in my_iter:
m_token_input = np.array(w1)
m_mask_input = w2
m_segment_input = np.array(w3)
m_memory_length_input = np.array(w4)
with self.graph.as_default():
predict = self.par_model.predict([m_token_input, m_segment_input, m_memory_length_input],
batch_size=self.batch_size)
for index, prob in enumerate(predict):
# pooled为句向量
pooled = sen_embed_cal(prob, m_mask_input[index])
pooled = pooled.tolist()
predicts.append(pooled)
return predicts
class KerasXlnetVector():
def __init__(self):
self.attention_type = ATTENTION_TYPE_BI if args.attention_type[
0] == 'bi' else ATTENTION_TYPE_UNI
self.memory_len, self.target_len, self.batch_size = args.memory_len, args.target_len, args.batch_size
self.checkpoint_path, self.config_path = args.ckpt_name, args.config_name
self.layer_indexes, self.in_train_phase = args.layer_indexes, False
print("load KerasXlnetEmbedding start! ")
# 全局使用，使其可以django、flask、tornado等调用
global graph
graph = tf.get_default_graph()
global model
# 模型加载
model = load_trained_model_from_checkpoint(
checkpoint_path=self.checkpoint_path,
attention_type=self.attention_type,
in_train_phase=self.in_train_phase,
config_path=self.config_path,
memory_len=self.memory_len,
target_len=self.target_len,
batch_size=self.batch_size,
mask_index=0)
# 字典加载
self.tokenizer = Tokenizer(args.spiece_model)
# debug时候查看layers
self.model_layers = model.layers
len_layers = self.model_layers.__len__()
print(len_layers)
len_couche = int((len_layers - 6) / 10)
# 一共246个layer
# 每层10个layer（MultiHeadAttention,Dropout,Add,LayerNormalization）,第一是9个layer的输入和embedding层
# 一共24层
layer_dict = [5]
layer_0 = 6
for i in range(len_couche):
layer_0 = layer_0 + 10
layer_dict.append(layer_0 - 2)
# 输出它本身
if len(self.layer_indexes) == 0:
encoder_layer = model.output
# 分类如果只有一层，取得不正确的话就取倒数第二层
elif len(self.layer_indexes) == 1:
if self.layer_indexes[0] in [i + 1 for i in range(len_couche + 1)]:
encoder_layer = model.get_layer(
index=layer_dict[self.layer_indexes[0]]).output
else:
encoder_layer = model.get_layer(index=layer_dict[-2]).output
# 否则遍历需要取的层，把所有层的weight取出来并加起来shape:768*层数
else:
# layer_indexes must be [0, 1, 2,3,......24]
all_layers = [
model.get_layer(index=layer_dict[lay]).output if lay
in [i + 1 for i in range(len_couche + 1)] else model.get_layer(
index=layer_dict[-2]).output # 如果给出不正确，就默认输出倒数第二层
for lay in self.layer_indexes
]
print(self.layer_indexes)
print(all_layers)
all_layers_select = []
for all_layers_one in all_layers:
all_layers_select.append(all_layers_one)
encoder_layer = Add()(all_layers_select)
print(encoder_layer.shape)
output_layer = NonMaskingLayer()(encoder_layer)
model = Model(model.inputs, output_layer)
print("load KerasXlnetEmbedding end")
model.summary(132)
def xlnet_encode(self, texts):
# 相当于pool，采用的是https://github.com/terrifyzhao/bert-utils/blob/master/graph.py
mul_mask = lambda x, m: x * np.expand_dims(m, axis=-1)
masked_reduce_mean = lambda x, m: np.sum(mul_mask(x, m), axis=1) / (
np.sum(m, axis=1, keepdims=True) + 1e-9)
# 文本预处理
predicts = []
for text in texts:
# print(text)
tokens = self.tokenizer.encode(text)
tokens = tokens + [0] * (self.target_len - len(tokens)) if len(
tokens) < self.target_len else tokens[0:self.target_len]
token_input = np.expand_dims(np.array(tokens), axis=0)
mask_input = np.array([0 if ids == 0 else 1 for ids in tokens])
segment_input = np.zeros_like(token_input)
memory_length_input = np.zeros((1, 1))
# 全局使用，使其可以django、flask、tornado等调用
with graph.as_default():
predict = model.predict(
[token_input, segment_input, memory_length_input],
batch_size=1)
# print(predict)
prob = predict[0]
pooled = masked_reduce_mean(prob, [mask_input])
pooled = pooled.tolist()
predicts.append(pooled[0])
return predicts
class XlnetEmbedding(BaseEmbedding):
def __init__(self, hyper_parameters):
self.layer_indexes = hyper_parameters['embedding'].get('layer_indexes', [24])
self.xlnet_embed = hyper_parameters['embedding'].get('xlnet_embed', {})
self.batch_size = hyper_parameters['model'].get('batch_size', 2)
super().__init__(hyper_parameters)
def build(self):
from keras_xlnet import Tokenizer, ATTENTION_TYPE_BI, ATTENTION_TYPE_UNI
from keras_xlnet import load_trained_model_from_checkpoint
self.embedding_type = 'xlnet'
self.checkpoint_path = os.path.join(self.corpus_path, 'xlnet_model.ckpt')
self.config_path = os.path.join(self.corpus_path, 'xlnet_config.json')
self.spiece_model = os.path.join(self.corpus_path, 'spiece.model')
self.attention_type = self.xlnet_embed.get('attention_type', 'bi') # or 'uni'
self.attention_type = ATTENTION_TYPE_BI if self.attention_type == 'bi' else ATTENTION_TYPE_UNI
self.memory_len = self.xlnet_embed.get('memory_len', 0)
self.target_len = self.xlnet_embed.get('target_len', 5)
print('load xlnet model start!')
# 模型加载
model = load_trained_model_from_checkpoint(checkpoint_path=self.checkpoint_path,
attention_type=self.attention_type,
in_train_phase=self.trainable,
config_path=self.config_path,
memory_len=self.memory_len,
target_len=self.target_len,
batch_size=self.batch_size,
mask_index=0)
# 字典加载
self.tokenizer = Tokenizer(self.spiece_model)
# debug时候查看layers
self.model_layers = model.layers
len_layers = self.model_layers.__len__()
print(len_layers)
len_couche = int((len_layers - 6) / 10)
# 一共246个layer
# 每层10个layer（MultiHeadAttention,Dropout,Add,LayerNormalization）,第一是9个layer的输入和embedding层
# 一共24层
layer_dict = [5]
layer_0 = 6
for i in range(len_couche):
layer_0 = layer_0 + 10
layer_dict.append(layer_0 - 2)
# 输出它本身
if len(self.layer_indexes) == 0:
encoder_layer = model.output
# 分类如果只有一层，取得不正确的话就取倒数第二层
elif len(self.layer_indexes) == 1:
if self.layer_indexes[0] in [i + 1 for i in range(len_couche + 1)]:
encoder_layer = model.get_layer(index=layer_dict[self.layer_indexes[0]]).output
else:
encoder_layer = model.get_layer(index=layer_dict[-1]).output
# 否则遍历需要取的层，把所有层的weight取出来并加起来shape:768*层数
else:
# layer_indexes must be [0, 1, 2,3,......24]
all_layers = [model.get_layer(index=layer_dict[lay]).output
if lay in [i + 1 for i in range(len_couche + 1)]
else model.get_layer(index=layer_dict[-1]).output # 如果给出不正确，就默认输出倒数第一层
for lay in self.layer_indexes]
print(self.layer_indexes)
print(all_layers)
all_layers_select = []
for all_layers_one in all_layers:
all_layers_select.append(all_layers_one)
encoder_layer = Add()(all_layers_select)
print(encoder_layer.shape)
self.output = NonMaskingLayer()(encoder_layer)
self.input = model.inputs
self.model = Model(model.inputs, self.output)
print("load KerasXlnetEmbedding end")
model.summary(132)
self.embedding_size = self.model.output_shape[-1]
self.vocab_size = len(self.tokenizer.sp)
def sentence2idx(self, text):
tokens = self.tokenizer.encode(text)
tokens = tokens + [0] * (self.target_len - len(tokens)) \
if len(tokens) < self.target_len \
else tokens[0:self.target_len]
token_input = np.expand_dims(np.array(tokens), axis=0)
segment_input = np.zeros_like(token_input)
memory_length_input = np.zeros((1, 1))
return [token_input, segment_input, memory_length_input]