问题
So far I have written following code:
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()
But I am getting error for softmax_w/b as uninitialized variables.
I am not getting how should I use these W and b and carry out train operation.
Something like following:
## some cost function
## training operation minimizing cost function using gradient descent optimizer
回答1:
tf.initialize_all_variables() gets the "current" set of variables from the graph. Since you are creating softmax_w and softmax_b after your call to tf.initialize_all_variables(), they are not in the list that tf.initialize_all_variables() consults, and hence not initialized when you run sess.run(init_op). The following should work :
softmax_w = tf.get_variable("softmax_w", [hidden_size, 1], )
softmax_b = tf.get_variable("softmax_b", [1])
init_op = tf.initialize_all_variables()
来源：https://stackoverflow.com/questions/38233056/how-can-i-complete-following-gru-based-rnn-written-in-tensorflow