import tensorflow as tf
import numpy as np
from bpemb import BPEmb
from tensorflow.contrib import rnn
batch_sz = 64
vocab_sz = 1000
embedding_dim = 100
units = 50
bpemb_en = BPEmb(lang = 'en', vs= vocab_sz, dim= embedding_dim)
max_length_inp = 10
max_length_target = 30
number_of_layers = 2
x = tf.placeholder('int32', shape= [None, max_length_inp])
y = tf.placeholder('float', shape= [None, max_length_target])
embedding_weights = tf.Variable(bpemb_en.vectors, trainable= False)
embed = tf.nn.embedding_lookup(embedding_weights, x)
def gru_cell():
return rnn.GRUCell(units)
cells = [gru_cell() for _ in range(4)]
def encoder(embed, batch_sz):
stacked_gru = rnn.MultiRNNCell(
[gru_cell() for _ in range(number_of_layers)])
outputs = []
state = stacked_gru.zero_state(batch_sz, tf.float32)
for i in range(max_length_inp):
output, state = stacked_gru(embed[:, i], state)
outputs.append(output)
outputs = tf.stack(outputs)
outputs = tf.transpose(outputs, [1, 0, 2])
return outputs, state[-1]
outputs, state = encoder(embed, batch_sz)
def attention(outputs, hidden):
hidden_with_time_axis = tf.expand_dims(hidden, 1)
score = tf.nn.tanh(tf.layers.dense(outputs, units) + tf.layers.dense(hidden_with_time_axis, units))
attention_weights = tf.nn.softmax(tf.layers.dense(score, 1), axis = 1)
context_vector = attention_weights * outputs
context_vector = tf.reduce_sum(context_vector, axis= 1)
return context_vector
contex_vector = attention(outputs, state)
def decoder(start, contex_vector, hidden, batch_sz):
def gru_cell():
return rnn.GRUCell(units)
stacked_gru_ = rnn.MultiRNNCell(
[gru_cell() for _ in range(number_of_layers)], state_is_tuple= False)
state = stacked_gru_.zero_state(batch_sz, tf.float32)
word_vector = tf.nn.embedding_lookup(embedding_weights, start)
result = []
for _ in range(max_length_target):
output, state = stacked_gru_(word_vector[:, 0], state)
result.append(output)
break
return result[0]
start = tf.placeholder('int32', [batch_sz, 1])
decoder(start, contex_vector, state, batch_sz)
ValueError: Variable multi_rnn_cell/cell_0/gru_cell/gates/kernel already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope? Originally defined at:
Ругается на output, state = stacked_gru_(word_vector[:, 0], state)
