我不能运行我的代码Tensorflow

Question

我上Ubuntu 14.04工作，我写的字母识别蒙山Tensorflow V 0.11代码， 我是创造一个代码源使用模型LeNet5 我的代码来源：

`

import PIL 

import numpy 
import tensorflow as tf 
# from tensorflow.examples.tutorials.mnist import input_data 
import Input as input_data 
from tensorflow.python.framework.importer import import_graph_def 

from Resize import Resize_img 

# these functions to optimize the accurancy of the mnist training 
#from imp_image import imp_img 
import scipy.misc 


def weight_variable(shape): 
    initial = tf.truncated_normal(shape, stddev=0.1) 
    return tf.Variable(initial) 


def bias_variable(shape): 
    initial = tf.constant(0.1, shape=shape) 
    return tf.Variable(initial) 


def conv2d(x, W): 
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') 


def max_pool_2x2(x): 
    return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') 


# ============================================================ End Functions part 

# mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) 

class MNIST: 

    def __init__(self): 

     # Open the compuation session 
     self.sess = tf.InteractiveSession() 
     # Load the network 
     self.Deep_Network() 

    def Deep_Network(self): 

     # nodes for the input images and target output classes. 
     # supervised classifier 
     self.x = tf.placeholder(tf.float32, shape=[None, 784]) 
     self.y_ = tf.placeholder(tf.float32, shape=[None, 10]) 

     # First convolutionanal Layer ===================================== 
     # It will consist of convolution, followed by max pooling 
     # The convolutional will compute 32 features for each 5x5 patch. 
     self.W_conv1 = weight_variable([5, 5, 1, 32]) 
     self.b_conv1 = bias_variable([32]) 

     # To apply the layer, we first reshape x to a 4d tensor, 
     # with the second and third dimensions corresponding to image width and height, 
     # and the final dimension corresponding to the number of color channels. 
     self.x_image = tf.reshape(self.x, [-1, 28, 28, 1]) 

     # We then convolve x_image with the weight tensor, add the bias, apply the ReLU function, and finally max pool. 
     self.h_conv1 = tf.nn.relu(conv2d(self.x_image, self.W_conv1) + self.b_conv1) 
     self.h_pool1 = max_pool_2x2(self.h_conv1) 

     # Second Convolutional Layer ===================================== 

     # In order to build a deep network, we stack several layers of this type. 
     # The second layer will have 64 features for each 5x5 patch. 

     self.W_conv2 = weight_variable([5, 5, 32, 64]) 
     self.b_conv2 = bias_variable([64]) 

     self.h_conv2 = tf.nn.relu(conv2d(self.h_pool1, self.W_conv2) + self.b_conv2) 
     self.h_pool2 = max_pool_2x2(self.h_conv2) 

     # Densely Connected Layer 

     # Now that the image size has been reduced to 7x7, we add a fully-connected layer with 1024 neurons 
     # to allow processing on the entire image. We reshape the tensor from the pooling layer into 
     # a batch of vectors, multiply by a weight matrix, add a bias, and apply a ReLU. 

     self.W_fc1 = weight_variable([7 * 7 * 64, 1024]) 
     self.b_fc1 = bias_variable([1024]) 

     self.h_pool2_flat = tf.reshape(self.h_pool2, [-1, 7 * 7 * 64]) 
     self.h_fc1 = tf.nn.relu(
      tf.matmul(self.h_pool2_flat, self.W_fc1) + self.b_fc1) # ReLu Computes rectified linear: max(features, 0). 

     # Dropout 

     self.keep_prob = tf.placeholder(tf.float32) 
     self.h_fc1_drop = tf.nn.dropout(self.h_fc1, self.keep_prob) 

     # Readout Layer ======================================== 
     # Finally, we add a softmax layer, just like for the one layer softmax regression above. 

     self.W_fc2 = weight_variable([1024, 10]) 
     self.b_fc2 = bias_variable([10]) 

     self.y_conv = tf.nn.softmax(tf.matmul(self.h_fc1_drop, self.W_fc2) + self.b_fc2) 
     self.cross_entropy = -tf.reduce_sum(self.y_ * tf.log(self.y_conv)) 
     self.correct_prediction = tf.equal(tf.argmax(self.y_conv, 1), tf.argmax(self.y_, 1)) 
     self.accuracy = tf.reduce_mean(tf.cast(self.correct_prediction, tf.float32)) 

    def Prediction(self, imageName): 

     # Load the trained model 
     ' Restore the model ' 
     'here i should create the model saver' 
     Saved_model_dir = '/home/brm17/Desktop/PFE/' 
     saver = tf.train.Saver() 
     ckpt = tf.train.get_checkpoint_state(Saved_model_dir) 

     'verifie if the saved model exists or not!' 
     if ckpt and ckpt.model_checkpoint_path: 
      saver.restore(self.sess, ckpt.model_checkpoint_path) 
     else: 
      print '# No saved model found!' 
      exit() # exit the prgm 

     # image_test = 'number-3.jpg' 
     ResizedImage = Resize_img(imageName) 

     ImageInput = ResizedImage.mnist_image_input.reshape(1, -1) 

     print 'Predection > ', tf.argmax(self.y_conv, 1).eval(feed_dict={self.x: ImageInput, self.keep_prob: 1.0}) 

    # print("test accuracy %g"%accuracy.eval(feed_dict={x: myTestImg, y_: myLabel, keep_prob: 1.0})) 


def main(): 
    image = '/home/brm17/Desktop/PFE/n2.jpeg' 
    model = MNIST() 
    model.Prediction(image) 

if __name__ == "__main__": 
    main() 

` 

如果我运行这段代码，他打印错误：

brm17@Brahim:~/Desktop/PFE$ python LeNet5.py 
Traceback (most recent call last): 
    File "LeNet5.py", line 137, in <module> 
    model.Prediction(image) 
    File "LeNet5.py", line 120, in Prediction 
    saver.restore(self.sess, ckpt.model_checkpoint_path) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1129, in restore 
    {self.saver_def.filename_tensor_name: save_path}) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 710, in run 
    run_metadata_ptr) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 908, in _run 
    feed_dict_string, options, run_metadata) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 958, in _do_run 
    target_list, options, run_metadata) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 978, in _do_call 
    raise type(e)(node_def, op, message) 
tensorflow.python.framework.errors.NotFoundError: Tensor name "Variable_1" not found in checkpoint files /home/brm17/Desktop/PFE/MNISTmodel-20000 
    [[Node: save/restore_slice_1 = RestoreSlice[dt=DT_FLOAT, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/restore_slice_1/tensor_name, save/restore_slice_1/shape_and_slice)]] 
Caused by op u'save/restore_slice_1', defined at: 
    File "LeNet5.py", line 137, in <module> 
    model.Prediction(image) 
    File "LeNet5.py", line 115, in Prediction 
    saver = tf.train.Saver() 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 861, in __init__ 
    restore_sequentially=restore_sequentially) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 519, in build 
    filename_tensor, vars_to_save, restore_sequentially, reshape) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 272, in _AddRestoreOps 
    values = self.restore_op(filename_tensor, vs, preferred_shard) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 187, in restore_op 
    preferred_shard=preferred_shard) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/io_ops.py", line 203, in _restore_slice 
    preferred_shard, name=name) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_io_ops.py", line 359, in _restore_slice 
    preferred_shard=preferred_shard, name=name) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 703, in apply_op 
    op_def=op_def) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2317, in create_op 
    original_op=self._default_original_op, op_def=op_def) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1239, in __init__ 
    self._traceback = _extract_stack() 

什么是p如何解决这个问题？

Answer 1

Covißio，

我认为这个问题是如下：

• 您创建了一个网络，并保存这个网络...
• 您更改了网络，并没有删除保存网络
• 现在，您尝试从旧版本重新加载网络，但您创建的新变量不存在。

你可以尝试两种：

• 删除网络的保存状态和再培训它
• 删除网络的保存和加载，看看这是否正常工作？ 您可以在您的文件夹/家庭删除检查点文件中删除您的网络的状态/ brm17 /桌面/ PFE/

编辑：仔细阅读你的代码，问题是，如果没有检查点，你不开始重新训练你的网络......也许你在保存，加载和改变你的网络之前先写这个。

祝你好运，让我知道如果这个工程！