Question

我正在尝试使用Keras实现将n嵌入1个序列的word2vec到序列模型。

我的代码

创建输入数据：

vec_x=[]
for sent in tok_x:
    sentvec = [ft_sg_model[w] for w in sent if w in ft_sg_model.wv.vocab]
    vec_x.append(sentvec)
vec_y=[]  
for sent in tok_y:
    sentvec = [ft_sg_model[w] for w in sent if w in ft_sg_model.wv.vocab]
    #print(sentvec)
    vec_y.append(sentvec)


for tok_sent in vec_x:
    tok_sent[maxlen-1:]=[]
    tok_sent.append(ft_sg_model['_E_'])

for tok_sent in vec_x:
    if len(tok_sent) < maxlen:
        for i in range(maxlen -len(tok_sent)):
            tok_sent.append(ft_sg_model['_E_'])

定义模型

import os
import pickle
import numpy as np
from keras.models import Sequential
import gensim
from keras.layers.recurrent import LSTM,SimpleRNN
from sklearn.model_selection import train_test_split
import theano
theano.config.optimizer="None"

vec_x=np.array(vec_x,dtype=np.float64)
vec_y=np.array(vec_y,dtype=np.float64) 


x_train,x_test, y_train,y_test = train_test_split(vec_x, vec_y, test_size=0.2, random_state=1)



model=Sequential()
print(y_train.shape[1:])
print(x_train.shape)

#model.add(LSTM(output_dim=300,input_shape=x_train.shape[1:],return_sequences=False, init='glorot_normal', inner_init='glorot_normal', activation='sigmoid',batch_size=1))
model.add(LSTM(output_dim=300,input_shape=x_train.shape[1:], activation='sigmoid'))
model.compile(loss='cosine_proximity', optimizer='adam', metrics=['accuracy'])
model.summary()

训练模型

model.fit(x_train, y_train, nb_epoch=500,validation_data=(x_test, y_test))
# This gives error
model.save('LSTM500.h5');

但是出现以下错误：

    /usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:1: UserWarning: The `nb_epoch` argument in `fit` has been renamed `epochs`.
      """Entry point for launching an IPython kernel.
    ---------------------------------------------------------------------------
    ValueError                                Traceback (most recent call last)
    <ipython-input-32-e9018df8d708> in <module>()
    ----> 1 model.fit(x_train, y_train, nb_epoch=500,validation_data=(x_test, y_test))
          2 model.save('LSTM500.h5');
          3 model.fit(x_train, y_train, nb_epoch=500,validation_data=(x_test, y_test))
          4 model.save('LSTM1000.h5');

    /usr/local/lib/python3.6/dist-packages/keras/engine/training.py in         fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split,         validation_data, shuffle, class_weight, sample_weight, initial_epoch,         steps_per_epoch, validation_steps, **kwargs)
        950             sample_weight=sample_weight,
        951             class_weight=class_weight,
    --> 952             batch_size=batch_size)
        953         # Prepare validation data.
        954         do_validation = False

    /usr/local/lib/python3.6/dist-packages/keras/engine/training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_array_lengths, batch_size)
        787                 feed_output_shapes,
        788                 check_batch_axis=False,  # Don't enforce the         batch size.
    --> 789                 exception_prefix='target')
        790 
        791             # Generate sample-wise weight values given the         `sample_weight` and

    /usr/local/lib/python3.6/dist-packages/keras/engine/training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
        126                         ': expected ' + names[i] + ' to have '         +        
        127                         str(len(shape)) + ' dimensions, but got array '
    --> 128                         'with shape ' + str(data_shape))
        129                 if not check_batch_axis:
        130                     data_shape = data_shape[1:]

    ValueError: Error when checking target: expected lstm_4 to have 2         dimensions, but got array with shape (525, 1, 300)

我是NLP和深度学习的新手，我对如何更改编码和目标感到困惑。请提供一些有关如何在代码中定义正确和最佳超参数的建议。

先谢谢您。

如何解决“检查目标时出错”？

0 个答案: