第二次运行tensorflow时出错
问题描述:
我想运行下面的tensorflow代码,它在第一次运行正常。如果我尝试再次运行它,它不断抛出一个错误说第二次运行tensorflow时出错
ValueError: Variable layer1/weights1 already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at:
File "C:\Users\owner\Anaconda3\envs\DeepLearning_NoGPU\lib\site-packages\tensorflow\python\framework\ops.py", line 1228, in __init__
self._traceback = _extract_stack()
File "C:\Users\owner\Anaconda3\envs\DeepLearning_NoGPU\lib\site-packages\tensorflow\python\framework\ops.py", line 2336, in create_op
original_op=self._default_original_op, op_def=op_def)
File "C:\Users\owner\Anaconda3\envs\DeepLearning_NoGPU\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 768, in apply_op
op_def=op_def)
如果我重新启动控制台,然后运行它,再一次它运行得很好。
以下给出了我对神经网络的实现。
import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler
import tensorflow as tf
learning_rate = 0.001
training_epochs = 100
n_input = 9
n_output = 1
n_layer1_node = 100
n_layer2_node = 100
X_train = np.random.rand(100, 9)
y_train = np.random.rand(100, 1)
with tf.variable_scope('input'):
X = tf.placeholder(tf.float32, shape=(None, n_input))
with tf.variable_scope('output'):
y = tf.placeholder(tf.float32, shape=(None, 1))
#layer 1
with tf.variable_scope('layer1'):
weight_matrix1 = {'weights': tf.get_variable(name='weights1',
shape=[n_input, n_layer1_node],
initializer=tf.contrib.layers.xavier_initializer()),
'biases': tf.get_variable(name='biases1',
shape=[n_layer1_node],
initializer=tf.zeros_initializer())}
layer1_output = tf.nn.relu(tf.add(tf.matmul(X, weight_matrix1['weights']), weight_matrix1['biases']))
#Layer 2
with tf.variable_scope('layer2'):
weight_matrix2 = {'weights': tf.get_variable(name='weights2',
shape=[n_layer1_node, n_layer2_node],
initializer=tf.contrib.layers.xavier_initializer()),
'biases': tf.get_variable(name='biases2',
shape=[n_layer2_node],
initializer=tf.zeros_initializer())}
layer2_output = tf.nn.relu(tf.add(tf.matmul(layer1_output, weight_matrix2['weights']), weight_matrix2['biases']))
#Output layer
with tf.variable_scope('layer3'):
weight_matrix3 = {'weights': tf.get_variable(name='weights3',
shape=[n_layer2_node, n_output],
initializer=tf.contrib.layers.xavier_initializer()),
'biases': tf.get_variable(name='biases3',
shape=[n_output],
initializer=tf.zeros_initializer())}
prediction = tf.nn.relu(tf.add(tf.matmul(layer2_output, weight_matrix3['weights']), weight_matrix3['biases']))
cost = tf.reduce_mean(tf.squared_difference(prediction, y))
optimizer = tf.train.AdamOptimizer(learning_rate).minimize(cost)
with tf.Session() as session:
session.run(tf.global_variables_initializer())
for epoch in range(training_epochs):
session.run(optimizer, feed_dict={X: X_train, y: y_train})
train_cost = session.run(cost, feed_dict={X: X_train, y:y_train})
print(epoch, " epoch(s) done")
print("training complete")
由于错误表明我尝试添加reuse=True
为with tf.variable_scope():
参数但再次无法正常工作。
我在conda环境中运行这个。我在Windows 10中使用Python 3.5和CUDA 8(但它应该没有关系,因为它没有配置为在GPU中运行)。
答
这是TF如何工作的问题。需要了解TF有一个“隐藏”状态 - 正在建立一个图表。大多数的tf函数在这个图中创建ops(就像每个tf.Variable调用,每个算术运算等一样)。另一方面,实际的“执行”发生在tf.Session()中。因此您的代码通常会是这样的:
build_graph()
with tf.Session() as sess:
process_something()
,因为所有的实际变量,结果等离开会议而已,如果你想“跑了两遍:”你会做
build_graph()
with tf.Session() as sess:
process_something()
with tf.Session() as sess:
process_something()
注意我正在建立图一次。图形是事物外观的抽象表示,它不包含任何计算状态。当你尝试做
build_graph()
with tf.Session() as sess:
process_something()
build_graph()
with tf.Session() as sess:
process_something()
你可能会得到第二build_graph(中)在试图创建具有相同名称的变量(在你的情况下会发生什么),图定稿等,如果你真的需要运行错误事情这样你只需要重置图表之间
build_graph()
with tf.Session() as sess:
process_something()
tf.reset_default_graph()
build_graph()
with tf.Session() as sess:
process_something()
将工作正常。