Tensor is not an element of this graph

Question

I\'m getting this error

\'ValueError: Tensor Tensor(\"Placeholder:0\", shape=(1, 1), dtype=int32) is not an element of this graph.\'

Answer 1

Inside def LoadPredictor(save):
Just after loading the model, add model._make_predict_function()
So the function becomes:

def LoadPredictor(save):
    with open(os.path.join(save, 'config.pkl'), 'rb') as f:
        saved_args = cPickle.load(f)
    with open(os.path.join(save, 'words_vocab.pkl'), 'rb') as f:
        words, vocab = cPickle.load(f)
    model = Model(saved_args, True)
    model._make_predict_function()
    return model, words, vocab

Answer 2

Use this line before making models:

keras.backend.clear_session()

This will make a new graph to use in new models.

Answer 3

When you create a Model, the session hasn't been restored yet. All placeholders, variables and ops that are defined in Model.__init__ are placed in a new graph, which makes itself a default graph inside with block. This is the key line:

with tf.Graph().as_default():
  ...

This means that this instance of tf.Graph() equals to tf.get_default_graph() instance inside with block, but not before or after it. From this moment on, there exist two different graphs.

When you later create a session and restore a graph into it, you can't access the previous instance of tf.Graph() in that session. Here's a short example:

with tf.Graph().as_default() as graph:
  var = tf.get_variable("var", shape=[3], initializer=tf.zeros_initializer)

# This works
with tf.Session(graph=graph) as sess:
  sess.run(tf.global_variables_initializer())
  print(sess.run(var))  # ok because `sess.graph == graph`

# This fails
saver = tf.train.import_meta_graph('/tmp/model.ckpt.meta')
with tf.Session() as sess:
  saver.restore(sess, "/tmp/model.ckpt")
  print(sess.run(var))   # var is from `graph`, not `sess.graph`!

The best way to deal with this is give names to all nodes, e.g. 'input', 'target', etc, save the model and then look up the nodes in the restored graph by name, something like this:

saver = tf.train.import_meta_graph('/tmp/model.ckpt.meta')
with tf.Session() as sess:
  saver.restore(sess, "/tmp/model.ckpt")      
  input_data = sess.graph.get_tensor_by_name('input')
  target = sess.graph.get_tensor_by_name('target')

This method guarantees that all nodes will be from the graph in session.

Answer 4

For me, this issue was resolved by using Keras' APIs to save and load model. I had more than one models being trained in my code and I had to use the particular model for prediction under a condition.

So I saved the entire model to a HDF5 file after model training

# The '.h5' extension indicates that the model should be saved to HDF5.
model.save('my_model.h5')

and then recreate/reload the saved model at the time of prediction

my_model = tf.keras.models.load_model('my_model.h5')

This helped me get rid of

*Tensor not an element of this graph*

error.

Answer 5

If you are calling the python function that calls Tensorflow from an external module, make sure that you the model isn't being loaded as a global variable or else it may not be loaded in time for usage. This happened to me calling a Tensorflow model from the Flask server.

Answer 6

Try first:

import tensorflow as tf
graph = tf.get_default_graph()

Then, when you need to use predict:

with graph.as_default():
     y = model.predict(X)