我正在尝试构建一个最简单的LSTM网络。只是希望它预测序列np_input_data
中的下一个值。
import tensorflow as tf
from tensorflow.python.ops import rnn_cell
import numpy as np
num_steps = 3
num_units = 1
np_input_data = [np.array([[1.],[2.]]), np.array([[2.],[3.]]), np.array([[3.],[4.]])]
batch_size = 2
graph = tf.Graph()
with graph.as_default():
tf_inputs = [tf.placeholder(tf.float32, [batch_size, 1]) for _ in range(num_steps)]
lstm = rnn_cell.BasicLSTMCell(num_units)
initial_state = state = tf.zeros([batch_size, lstm.state_size])
loss = 0
for i in range(num_steps-1):
output, state = lstm(tf_inputs[i], state)
loss += tf.reduce_mean(tf.square(output - tf_inputs[i+1]))
with tf.Session(graph=graph) as session:
tf.initialize_all_variables().run()
feed_dict={tf_inputs[i]: np_input_data[i] for i in range(len(np_input_data))}
loss = session.run(loss, feed_dict=feed_dict)
print(loss)
口译员返回:
ValueError: Variable BasicLSTMCell/Linear/Matrix already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at:
output, state = lstm(tf_inputs[i], state)
我做错了什么?
答案 0 :(得分:5)
此处呼叫lstm
:
for i in range(num_steps-1):
output, state = lstm(tf_inputs[i], state)
将尝试每次迭代创建具有相同名称的变量,除非您另有说明。您可以使用tf.variable_scope
with tf.variable_scope("myrnn") as scope:
for i in range(num_steps-1):
if i > 0:
scope.reuse_variables()
output, state = lstm(tf_inputs[i], state)
第一次迭代创建表示LSTM参数的变量,每次后续迭代(在调用reuse_variables
之后)都会按名称在范围内查找它们。
答案 1 :(得分:5)
我使用tf.nn.dynamic_rnn
在TensorFlow v1.0.1中遇到了类似的问题。事实证明,如果我必须在训练过程中重新训练或取消并重新开始我的训练过程,那么错误才会出现。基本上图表没有重置。
长话短说,在代码的开头抛出一个tf.reset_default_graph()
它应该会有所帮助。至少在使用tf.nn.dynamic_rnn
和再培训时。
答案 2 :(得分:1)
使用tf.nn.rnn
或tf.nn.dynamic_rnn
执行此操作,以及许多其他好事,为您服务。