我怎样才能完成以下用 tensorflow 编写的基于 GRU 的 RNN?

How can I complete following GRU based RNN written in tensorflow?

到目前为止,我已经编写了以下代码:

import pickle
import numpy as np
import pandas as pd
import tensorflow as tf

# load pickled objects (x and y)
x_input, y_actual = pickle.load(open('sample_input.pickle', 'rb'))
x_input = np.reshape(x_input, (50, 1))
y_actual = np.reshape(y_actual, (50, 1))

# parameters
batch_size = 50
hidden_size = 100

# create network graph
input_data = tf.placeholder(tf.float32, [batch_size, 1])
output_data = tf.placeholder(tf.float32, [batch_size, 1])

cell = tf.nn.rnn_cell.GRUCell(hidden_size)

initial_state = cell.zero_state(batch_size, tf.float32)

hidden_state = initial_state

output_of_cell, hidden_state = cell(inputs=input_data, state=hidden_state)

init_op = tf.initialize_all_variables()

softmax_w = tf.get_variable("softmax_w", [hidden_size, 1], )
softmax_b = tf.get_variable("softmax_b", [1])

logits = tf.matmul(output_of_cell, softmax_w) + softmax_b

probabilities = tf.nn.softmax(logits)

sess = tf.Session()
sess.run(init_op)

something = sess.run([probabilities, hidden_state], feed_dict={input_data:x_input, output_data:y_actual})

#cost = tf.nn.sigmoid_cross_entropy_with_logits(logits, output_data)


#sess.close()

但是我收到 softmax_w/b 作为未初始化变量的错误。

我不知道我应该如何使用这些 Wb 并进行火车操作。

类似于以下内容:

## some cost function
## training operation minimizing cost function using gradient descent optimizer

tf.initialize_all_variables() 从图中获取 "current" 组变量。由于您是在调用 tf.initialize_all_variables() 之后创建 softmax_wsoftmax_b,它们不在 tf.initialize_all_variables() 查询的列表中,因此当您 运行 时它们不会被初始化sess.run(init_op)。以下应该有效:

softmax_w = tf.get_variable("softmax_w", [hidden_size, 1], )
softmax_b = tf.get_variable("softmax_b", [1])

init_op = tf.initialize_all_variables()