как отключить дату во времени выполнения в xpath Java?

В указанном руководстве, он выбирает использовать theano вместо tensorflow, потому что поведение dot в tensorflow отличается от поведения в numpy. Но я не знаком с theano, поэтому мне сложно заставить его работать правильно, используя theano бэкэнд. Я скорее использую серию операций, чтобы имитировать поведение dot в numpy. После я изменил K.dot на серию операций.

import tensorflow as tf
import numpy as np
import pandas as pd
import re
from bs4 import BeautifulSoup
import os
from keras.preprocessing.text import Tokenizer, text_to_word_sequence
from keras.utils import plot_model
from keras.utils.np_utils import to_categorical
from keras.layers import Dense, Input
from keras.layers import Embedding, GRU, Bidirectional, TimeDistributed, Lambda
from keras.models import Model
from keras import backend as K
from keras.engine.topology import Layer
from keras import initializers

class AttLayer(Layer):
    def __init__(self, attention_dim, **kwargs):
        self.init = initializers.get('normal')
        self.supports_masking = True
        self.attention_dim = attention_dim
        super(AttLayer, self).__init__(**kwargs)

    def build(self, input_shape):
        assert len(input_shape) == 3
        self.W = K.variable(self.init((input_shape[-1], self.attention_dim)))
        self.b = K.variable(self.init((self.attention_dim,)))
        self.u = K.variable(self.init((self.attention_dim, 1)))
        self.trainable_weights = [self.W, self.b, self.u]
        super(AttLayer, self).build(input_shape)

    def compute_mask(self, inputs, mask=None):
        return None

    def call(self, x, mask=None):
        # size of x :[batch_size, sel_len, attention_dim]
        # size of u :[batch_size, attention_dim]
        # uit = tanh(xW+b)
        uit = K.tile(K.expand_dims(self.W, axis=0), (K.shape(x)[0], 1, 1))
        uit = tf.matmul(x, uit)
        uit = K.tanh(K.bias_add(uit, self.b))
        ait = K.dot(uit, self.u)
        ait = K.squeeze(ait, -1)

        ait = K.exp(ait)

        if mask is not None:
            # Cast the mask to floatX to avoid float64 upcasting in theano
            ait *= K.cast(mask, K.floatx())
        ait /= K.cast(K.sum(ait, axis=1, keepdims=True) + K.epsilon(), K.floatx())
        ait = K.expand_dims(ait)
        weighted_input = x * ait
        output = K.sum(weighted_input, axis=1)

        return output

    def compute_output_shape(self, input_shape):
        return (input_shape[0], input_shape[-1])

    # https://github.com/keras-team/keras/issues/5401
    # solve the problem of keras.models.clone_model
    # and model.save_weights, model.load_weights
    def get_config(self):
        config = {'attention_dim': self.attention_dim}
        base_config = super(AttLayer, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))

Также compute_mask теперь возвращает None, потому что в выводе AttLayer нет оси sel_len.

Ниже приведен скрипт, подтверждающий, что эти две операции эквивалентны:

B = 8
S = 100
E = 200
A = 50
X = np.random.randn(B, S, E)
W = np.random.randn(E, A)
np_result = np.dot(X, W) #shape correct

X_ph = tf.placeholder(tf.float64)
W_ph = tf.placeholder(tf.float64)

tf_dot = tf.matmul(X_ph, 
                   tf.tile(
                           tf.expand_dims(W_ph, axis=0),
                           (K.shape(X_ph)[0], 1, 1)))

with tf.Session() as sess:
    tf_result = sess.run(tf_dot,
                         feed_dict = {X_ph:X, W_ph:W})

print(np.allclose(np_result, tf_result)) #True

История обучения (я установил batch_size как 8):

Train on 20000 samples, validate on 5000 samples
Epoch 1/10
20000/20000 [==============================] - 1247s 62ms/step - loss: 0.4203 - acc: 0.8044 - val_loss: 0.3520 - val_acc: 0.8468
Epoch 2/10
20000/20000 [==============================] - 985s 49ms/step - loss: 0.2344 - acc: 0.9070 - val_loss: 0.3411 - val_acc: 0.8586
Epoch 3/10
20000/20000 [==============================] - 996s 50ms/step - loss: 0.0982 - acc: 0.9628 - val_loss: 0.4474 - val_acc: 0.8512
Epoch 4/10
20000/20000 [==============================] - 966s 48ms/step - loss: 0.0285 - acc: 0.9904 - val_loss: 0.7837 - val_acc: 0.8408
Epoch 5/10
20000/20000 [==============================] - 912s 46ms/step - loss: 0.0179 - acc: 0.9936 - val_loss: 1.0177 - val_acc: 0.8440
Epoch 6/10
20000/20000 [==============================] - 910s 45ms/step - loss: 0.0105 - acc: 0.9963 - val_loss: 1.0635 - val_acc: 0.8418
Epoch 7/10
20000/20000 [==============================] - 909s 45ms/step - loss: 0.0101 - acc: 0.9964 - val_loss: 1.0966 - val_acc: 0.8372
Epoch 8/10
20000/20000 [==============================] - 909s 45ms/step - loss: 0.0057 - acc: 0.9981 - val_loss: 1.2678 - val_acc: 0.8392
Epoch 9/10
20000/20000 [==============================] - 910s 46ms/step - loss: 0.0077 - acc: 0.9974 - val_loss: 1.2166 - val_acc: 0.8258
Epoch 10/10
20000/20000 [==============================] - 910s 46ms/step - loss: 0.0056 - acc: 0.9985 - val_loss: 1.4640 - val_acc: 0.8204