我在Ubuntu 14.04工作，我写了一个代码来识别Tensorflow V 0.11的字母，
我创建了一个使用模型LeNet5的代码源
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()
`
如果我运行此代码，他会打印错误：
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()
问题是什么以及如何解决这个问题？
答案 0 :(得分：0)
Covißio，
我认为问题如下：
你可以尝试：
编辑：彻底阅读您的代码，问题是如果没有检查点，您就不会开始重新训练网络......也许您可以在保存，加载和更改网络之前编写此代码。
祝你好运，如果有效，请告诉我！