Tensorflow:variable_scope的值错误 [英] Tensorflow: value error with variable_scope

问题描述

这是我的下面的代码:

'''
Tensorflow LSTM classification of 16x30 images.
'''

from __future__ import print_function

import tensorflow as tf
from tensorflow.python.ops import rnn, rnn_cell
import numpy as np
from numpy import genfromtxt
from sklearn.cross_validation import train_test_split
import pandas as pd

'''
a Tensorflow LSTM that will sequentially input several lines from each single image 
i.e. The Tensorflow graph will take a flat (1,480) features image as it was done in Multi-layer
perceptron MNIST Tensorflow tutorial, but then reshape it in a sequential manner with 16 features each and 30 time_steps.
'''

blaine = genfromtxt('./Desktop/Blaine_CSV_lstm.csv',delimiter=',')  # CSV transform to array
target = [row[0] for row in blaine]             # 1st column in CSV as the targets
data = blaine[:, 1:481]                          #flat feature vectors
X_train, X_test, y_train, y_test = train_test_split(data, target, test_size=0.05, random_state=42)

f=open('cs-training.csv','w')       #1st split for training
for i,j in enumerate(X_train):
        k=np.append(np.array(y_train[i]),j   )
        f.write(",".join([str(s) for s in k]) + '\n')
f.close()
f=open('cs-testing.csv','w')        #2nd split for test
for i,j in enumerate(X_test):
        k=np.append(np.array(y_test[i]),j   )
        f.write(",".join([str(s) for s in k]) + '\n')
f.close()



new_data = genfromtxt('cs-training.csv',delimiter=',')  # Training data
new_test_data = genfromtxt('cs-testing.csv',delimiter=',')  # Test data

x_train=np.array([ i[1::] for i in new_data])
ss = pd.Series(y_train)     #indexing series needed for later Pandas Dummies one-hot vectors
y_train_onehot = pd.get_dummies(ss)

x_test=np.array([ i[1::] for i in new_test_data])
gg = pd.Series(y_test)
y_test_onehot = pd.get_dummies(gg)


# General Parameters
learning_rate = 0.001
training_iters = 100000
batch_size = 33
display_step = 10

# Tensorflow LSTM Network Parameters
n_input = 16 # MNIST data input (img shape: 28*28)
n_steps = 30 # timesteps
n_hidden = 128 # hidden layer num of features
n_classes = 20 # MNIST total classes (0-9 digits)

# tf Graph input
x = tf.placeholder("float", [None, n_steps, n_input])
y = tf.placeholder("float", [None, n_classes])

# Define weights

weights = {
    'out': tf.Variable(tf.random_normal([n_hidden, n_classes]))
}
biases = {
    'out': tf.Variable(tf.random_normal([n_classes]))
}


def RNN(x, weights, biases):

    # Prepare data shape to match `rnn` function requirements
    # Current data input shape: (batch_size, n_steps, n_input)
    # Required shape: 'n_steps' tensors list of shape (batch_size, n_input)

    # Permuting batch_size and n_steps
    x = tf.transpose(x, [1, 0, 2])
    # Reshaping to (n_steps*batch_size, n_input)
    x = tf.reshape(x, [-1, n_input])
    # Split to get a list of 'n_steps' tensors of shape (batch_size, n_input)
    x = tf.split(0, n_steps, x)

    # Define a lstm cell with tensorflow
    with tf.variable_scope('cell_def'): 
        lstm_cell = tf.nn.rnn_cell.LSTMCell(n_hidden, forget_bias=1.0)

    # Get lstm cell output
    with tf.variable_scope('rnn_def'): 
        outputs, states = tf.nn.rnn(lstm_cell, x, dtype=tf.float32)

    # Linear activation, using rnn inner loop last output
    return tf.matmul(outputs[-1], weights['out']) + biases['out']

pred = RNN(x, weights, biases)

# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

# Evaluate model
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))

# Initializing the variables
init = tf.initialize_all_variables()

# Launch the graph
with tf.Session() as sess:
    sess.run(init)
    step = 1
    # Keep training until reach max iterations
    while step * batch_size < training_iters:
        batch_x = np.split(x_train, 15)
        batch_y = np.split(y_train_onehot, 15)
        for index in range(len(batch_x)):
            ouh1 = batch_x[index]
            ouh2 = batch_y[index]
            # Reshape data to get 28 seq of 28 elements
            ouh1 = np.reshape(ouh1,(batch_size, n_steps, n_input))        
            sess.run(optimizer, feed_dict={x: ouh1, y: ouh2})      # Run optimization op (backprop)
            if step % display_step == 0:
                # Calculate batch accuracy
                acc = sess.run(accuracy, feed_dict={x: ouh1, y: ouh2})
                # Calculate batch loss
                loss = sess.run(cost, feed_dict={x: ouh1, y: ouh2})
                print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
                    "{:.6f}".format(loss) + ", Training Accuracy= " + \
                    "{:.5f}".format(acc))
                step += 1
print("Optimization Finished!")

并且我收到以下错误，似乎我在第92和97行上对同一变量进行了重复，并且我担心这可能是与RNN def端上的Tensorflow 0.10.0不兼容的情况:

and I am getting the below error that it seems i am re-iterating over the same variable on lines 92 and 97, and i am concerned that it might be a case of incompatibility with Tensorflow 0.10.0 on the RNN def side:

ValueError: Variable RNN/BasicLSTMCell/Linear/Matrix already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at:

  File "/home/mohsen/lstm_mnist.py", line 92, in RNN
    outputs, states = tf.nn.rnn(lstm_cell, x, dtype=tf.float32)
  File "/home/mohsen/lstm_mnist.py", line 97, in <module>
    pred = RNN(x, weights, biases)
  File "/home/mohsen/anaconda2/lib/python2.7/site-packages/spyderlib/widgets/externalshell/sitecustomize.py", line 81, in execfile
    builtins.execfile(filename, *where)

此错误的起因是什么，我该如何解决?

What could be the origin of this error and how i can resolve it?

在我基于代码构建的原始存储库中，同样的variable_scope问题仍然存在

from the original repo where i build upon my code the same variable_scope problem persists https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py

推荐答案

您不会在第92和97行中迭代相同的变量，因为这些变量将始终位于同一命名空间中，至少在当前设置中，因为您正在从另一个内部调用一个名称空间(因为一个名称空间已嵌入RNN函数中).因此，您的有效变量范围将类似于'backward/forward'.

You are not iterating over the same variable in line 92 and 97, since those will always be in the same namespace, at least in the current setting, since you are calling one namespace from within another (since one is embedded in the RNN function). So your effective variable scope will be something like 'backward/forward'.

因此，我认为问题出在第89行和第92行，因为两者都生活"在同一个名称空间中(请参见上文)，并且两者都可能引入名为RNN/BasicLSTMCell/Linear/Matrix的变量.因此，您应该将代码更改为以下内容:

Hence the problem, in my guess, is in lines 89 and 92, since both "live" in the same namespace (see above), and both may introduce a variable called RNN/BasicLSTMCell/Linear/Matrix. So you should change your code to the following:

# Define a lstm cell with tensorflow
with tf.variable_scope('cell_def'):
    lstm_cell = tf.nn.rnn_cell.LSTMCell(n_hidden, forget_bias=1.0)

# Get lstm cell output
with tf.variable_scope('rnn_def'):
    outputs, states = tf.nn.rnn(lstm_cell, x, dtype=tf.float32)

这使得LSTMCell初始化存在于一个命名空间-"cell_def/*"中，而完整RNN的初始化存在于另一个命名空间-"rnn_def/*"中.

This makes the LSTMCell initialization live in one namespace - "cell_def/*", and the initialization of the complete RNN in another - "rnn_def/*".

这篇关于Tensorflow:variable_scope的值错误的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！