No variable to save error in Tensorflow

kkk picture kkk · Mar 29, 2016 · Viewed 33.2k times · Source

I am trying to save the model and then reuse it for classifying my images but unfortunately i am getting errors in restoring the model that i have saved.

The code in which model has been created :

# Deep Learning
# =============
# 
# Assignment 4
# ------------

# In[25]:

# These are all the modules we'll be using later. Make sure you can import them
# before proceeding further.
from __future__ import print_function
import numpy as np
import tensorflow as tf
from six.moves import cPickle as pickle
from six.moves import range


# In[37]:

pickle_file = 'notMNIST.pickle'

with open(pickle_file, 'rb') as f:
  save = pickle.load(f)
  train_dataset = save['train_dataset']
  train_labels = save['train_labels']
  valid_dataset = save['valid_dataset']
  valid_labels = save['valid_labels']
  test_dataset = save['test_dataset']
  test_labels = save['test_labels']
  del save  # hint to help gc free up memory
  print('Training set', train_dataset.shape, train_labels.shape)
  print('Validation set', valid_dataset.shape, valid_labels.shape)
  print('Test set', test_dataset.shape, test_labels.shape)
  print(test_labels)


# Reformat into a TensorFlow-friendly shape:
# - convolutions need the image data formatted as a cube (width by height by #channels)
# - labels as float 1-hot encodings.

# In[38]:

image_size = 28
num_labels = 10
num_channels = 1 # grayscale

import numpy as np

def reformat(dataset, labels):
  dataset = dataset.reshape(
    (-1, image_size, image_size, num_channels)).astype(np.float32)
  #print(np.arange(num_labels))
  labels = (np.arange(num_labels) == labels[:,None]).astype(np.float32)
  #print(labels[0,:])
  print(labels[0])
  return dataset, labels
train_dataset, train_labels = reformat(train_dataset, train_labels)
valid_dataset, valid_labels = reformat(valid_dataset, valid_labels)
test_dataset, test_labels = reformat(test_dataset, test_labels)
print('Training set', train_dataset.shape, train_labels.shape)
print('Validation set', valid_dataset.shape, valid_labels.shape)
print('Test set', test_dataset.shape, test_labels.shape)
#print(labels[0])


# In[39]:

def accuracy(predictions, labels):
  return (100.0 * np.sum(np.argmax(predictions, 1) == np.argmax(labels, 1))
          / predictions.shape[0])


# Let's build a small network with two convolutional layers, followed by one fully connected layer. Convolutional networks are more expensive computationally, so we'll limit its depth and number of fully connected nodes.

# In[47]:

batch_size = 16
patch_size = 5
depth = 16
num_hidden = 64

graph = tf.Graph()

with graph.as_default():

  # Input data.
  tf_train_dataset = tf.placeholder(
    tf.float32, shape=(batch_size, image_size, image_size, num_channels))
  tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))
  tf_valid_dataset = tf.constant(valid_dataset)
  tf_test_dataset = tf.constant(test_dataset)

  # Variables.
  layer1_weights = tf.Variable(tf.truncated_normal(
      [patch_size, patch_size, num_channels, depth], stddev=0.1),name="layer1_weights")
  layer1_biases = tf.Variable(tf.zeros([depth]),name = "layer1_biases")
  layer2_weights = tf.Variable(tf.truncated_normal(
      [patch_size, patch_size, depth, depth], stddev=0.1),name = "layer2_weights")
  layer2_biases = tf.Variable(tf.constant(1.0, shape=[depth]),name ="layer2_biases")
  layer3_weights = tf.Variable(tf.truncated_normal(
      [image_size // 4 * image_size // 4 * depth, num_hidden], stddev=0.1),name="layer3_biases")
  layer3_biases = tf.Variable(tf.constant(1.0, shape=[num_hidden]),name = "layer3_biases")
  layer4_weights = tf.Variable(tf.truncated_normal(
      [num_hidden, num_labels], stddev=0.1),name = "layer4_weights")
  layer4_biases = tf.Variable(tf.constant(1.0, shape=[num_labels]),name = "layer4_biases")

  # Model.
  def model(data):
    conv = tf.nn.conv2d(data, layer1_weights, [1, 2, 2, 1], padding='SAME')
    hidden = tf.nn.relu(conv + layer1_biases)
    conv = tf.nn.conv2d(hidden, layer2_weights, [1, 2, 2, 1], padding='SAME')
    hidden = tf.nn.relu(conv + layer2_biases)
    shape = hidden.get_shape().as_list()
    reshape = tf.reshape(hidden, [shape[0], shape[1] * shape[2] * shape[3]])
    hidden = tf.nn.relu(tf.matmul(reshape, layer3_weights) + layer3_biases)
    return tf.matmul(hidden, layer4_weights) + layer4_biases

  # Training computation.
  logits = model(tf_train_dataset)
  loss = tf.reduce_mean(
    tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))

  # Optimizer.
  optimizer = tf.train.GradientDescentOptimizer(0.05).minimize(loss)

  # Predictions for the training, validation, and test data.
  train_prediction = tf.nn.softmax(logits)
  valid_prediction = tf.nn.softmax(model(tf_valid_dataset))
  test_prediction = tf.nn.softmax(model(tf_test_dataset))


# In[48]:

num_steps = 1001
#saver = tf.train.Saver()
with tf.Session(graph=graph) as session:
  tf.initialize_all_variables().run()
  print('Initialized')
  for step in range(num_steps):
    offset = (step * batch_size) % (train_labels.shape[0] - batch_size)
    batch_data = train_dataset[offset:(offset + batch_size), :, :, :]
    batch_labels = train_labels[offset:(offset + batch_size), :]
    feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels}
    _, l, predictions = session.run(
      [optimizer, loss, train_prediction], feed_dict=feed_dict)
    if (step % 50 == 0):
      print('Minibatch loss at step %d: %f' % (step, l))
      print('Minibatch accuracy: %.1f%%' % accuracy(predictions, batch_labels))
      print('Validation accuracy: %.1f%%' % accuracy(
        valid_prediction.eval(), valid_labels))
  print('Test accuracy: %.1f%%' % accuracy(test_prediction.eval(), test_labels))
  save_path = tf.train.Saver().save(session, "/tmp/model.ckpt")
  print("Model saved in file: %s" % save_path)

Everything works fine and the model is stored in the respective folder .

I have created one more python file where i have tried restoring the model but getting an error there

# In[1]:
from __future__ import print_function
import numpy as np
import tensorflow as tf
from six.moves import cPickle as pickle
from six.moves import range


# In[3]:

image_size = 28
num_labels = 10
num_channels = 1 # grayscale
import numpy as np


# In[4]:

def accuracy(predictions, labels):
  return (100.0 * np.sum(np.argmax(predictions, 1) == np.argmax(labels, 1))
          / predictions.shape[0])


# In[8]:

batch_size = 16
patch_size = 5
depth = 16
num_hidden = 64

graph = tf.Graph()

with graph.as_default():

  '''# Input data.
  tf_train_dataset = tf.placeholder(
    tf.float32, shape=(batch_size, image_size, image_size, num_channels))
  tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))
  tf_valid_dataset = tf.constant(valid_dataset)
  tf_test_dataset = tf.constant(test_dataset)'''

  # Variables.
  layer1_weights = tf.Variable(tf.truncated_normal(
      [patch_size, patch_size, num_channels, depth], stddev=0.1),name="layer1_weights")
  layer1_biases = tf.Variable(tf.zeros([depth]),name = "layer1_biases")
  layer2_weights = tf.Variable(tf.truncated_normal(
      [patch_size, patch_size, depth, depth], stddev=0.1),name = "layer2_weights")
  layer2_biases = tf.Variable(tf.constant(1.0, shape=[depth]),name ="layer2_biases")
  layer3_weights = tf.Variable(tf.truncated_normal(
      [image_size // 4 * image_size // 4 * depth, num_hidden], stddev=0.1),name="layer3_biases")
  layer3_biases = tf.Variable(tf.constant(1.0, shape=[num_hidden]),name = "layer3_biases")
  layer4_weights = tf.Variable(tf.truncated_normal(
      [num_hidden, num_labels], stddev=0.1),name = "layer4_weights")
  layer4_biases = tf.Variable(tf.constant(1.0, shape=[num_labels]),name = "layer4_biases")

  # Model.
  def model(data):
    conv = tf.nn.conv2d(data, layer1_weights, [1, 2, 2, 1], padding='SAME')
    hidden = tf.nn.relu(conv + layer1_biases)
    conv = tf.nn.conv2d(hidden, layer2_weights, [1, 2, 2, 1], padding='SAME')
    hidden = tf.nn.relu(conv + layer2_biases)
    shape = hidden.get_shape().as_list()
    reshape = tf.reshape(hidden, [shape[0], shape[1] * shape[2] * shape[3]])
    hidden = tf.nn.relu(tf.matmul(reshape, layer3_weights) + layer3_biases)
    return tf.matmul(hidden, layer4_weights) + layer4_biases

  '''# Training computation.
  logits = model(tf_train_dataset)
  loss = tf.reduce_mean(
    tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))

  # Optimizer.
  optimizer = tf.train.GradientDescentOptimizer(0.05).minimize(loss)'''

  # Predictions for the training, validation, and test data.
  #train_prediction = tf.nn.softmax(logits)
  #valid_prediction = tf.nn.softmax(model(tf_valid_dataset))
  #test_prediction = tf.nn.softmax(model(tf_test_dataset))

# In[17]:

#saver = tf.train.Saver()
with tf.Session() as sess:
  # Restore variables from disk.
  tf.train.Saver().restore(sess, "/tmp/model.ckpt")
  print("Model restored.")
  # Do some work with the model

error that i am getting is :

No variables to save

Any help would be appreciated

Answer

mrry picture mrry · Mar 29, 2016

The error here is quite subtle. In In[8] you create a tf.Graph called graph and set it as default for the with graph.as_default(): block. This means that all of the variables are created in graph, and if you print graph.all_variables() you should see a list of your variables.

However, you exit the with block before creating (i) the tf.Session, and (ii) the tf.train.Saver. This means that the session and saver are created in a different graph (the global default tf.Graph that is used when you don't explicitly create one and set it as default), which doesn't contain any variables—or any nodes at all.

There are at least two solutions:

  1. As Yaroslav suggests, you can write your program without using the with graph.as_default(): block, which avoids the confusion with multiple graphs. However, this can lead to name collisions between different cells in your IPython notebook, which is awkward when using the tf.train.Saver, since it uses the name property of a tf.Variable as the key in the checkpoint file.

  2. You can create the saver inside the with graph.as_default(): block, and create the tf.Session with an explicit graph, as follows:

    with graph.as_default():
        # [Variable and model creation goes here.]
    
        saver = tf.train.Saver()  # Gets all variables in `graph`.
    
    with tf.Session(graph=graph) as sess:
        saver.restore(sess)
        # Do some work with the model....
    

    Alternatively, you can create the tf.Session inside the with graph.as_default(): block, in which case it will use graph for all of its operations.