第二次运行tensorflow时出错

Question

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

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）。

Answer 1

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。