AttributeError: module 'tensorflow' has no attribute 'get_default_graph'

Question

I am doing some task related to image captioning and I have loaded the weights of inception model like this

model = InceptionV3(weights='imagenet')

But I am getting error like this:

AttributeError: module 'tensorflow' has no attribute 'get_default_graph'

What should I do? Please help. Here is the full output of above code.

1 . --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in () 1 # Load the inception v3 model ----> 2 model = InceptionV3(include_top=True,weights='imagenet') 3 # InceptionV3(weights='imagenet')

~/anaconda3/lib/python3.6/site-packages/keras/applications/__init__.py
in wrapper(*args, **kwargs)
     26             kwargs['models'] = models
     27             kwargs['utils'] = utils
---> 28         return base_fun(*args, **kwargs)
     29 
     30     return wrapper

~/anaconda3/lib/python3.6/site-packages/keras/applications/inception_v3.py
in InceptionV3(*args, **kwargs)
      9 @keras_modules_injection
     10 def InceptionV3(*args, **kwargs):
---> 11     return inception_v3.InceptionV3(*args, **kwargs)
     12 
     13 

~/anaconda3/lib/python3.6/site-packages/keras_applications/inception_v3.py
in InceptionV3(include_top, weights, input_tensor, input_shape,
pooling, classes, **kwargs)
    155 
    156     if input_tensor is None:
--> 157         img_input = layers.Input(shape=input_shape)
    158     else:
    159         if not backend.is_keras_tensor(input_tensor):

~/anaconda3/lib/python3.6/site-packages/keras/engine/input_layer.py
in Input(shape, batch_shape, name, dtype, sparse, tensor)
    176                              name=name, dtype=dtype,
    177                              sparse=sparse,
--> 178                              input_tensor=tensor)
    179     # Return tensor including _keras_shape and _keras_history.
    180     # Note that in this case train_output and test_output are the same pointer.

~/anaconda3/lib/python3.6/site-packages/keras/legacy/interfaces.py
in wrapper(*args, **kwargs)
     89                 warnings.warn('Update your `' + object_name + '` call to the ' +
     90                               'Keras 2 API: ' + signature, stacklevel=2)
---> 91             return func(*args, **kwargs)
     92         wrapper._original_function = func
     93         return wrapper

~/anaconda3/lib/python3.6/site-packages/keras/engine/input_layer.py
in __init__(self, input_shape, batch_size, batch_input_shape, dtype,
input_tensor, sparse, name)
     37         if not name:
     38             prefix = 'input'
---> 39             name = prefix + '_' + str(K.get_uid(prefix))
     40         super(InputLayer, self).__init__(dtype=dtype, name=name)
     41 

~/anaconda3/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py
in get_uid(prefix)
     72     """
     73     global _GRAPH_UID_DICTS
---> 74     graph = tf.get_default_graph()
     75     if graph not in _GRAPH_UID_DICTS:
     76         _GRAPH_UID_DICTS[graph] = defaultdict(int)

AttributeError: module 'tensorflow' has no attribute
'get_default_graph'

Do you have a file called tensorflow.py in your codebase? How did you install tensorflow? — Dr. Snoopy
– Dr. Snoopy, Commented Mar 19, 2019 at 9:07
@Vlad thanks for the reply but i resolved this issue after updating keras,tensorflow,and conda 's all packages . — Ayush Kushwaha
– Ayush Kushwaha, Commented Mar 19, 2019 at 21:13
@MatiasValdenegro thanks for your reply but i resolved this issue after updating keras,tensorflow,and conda 's all packages and i don't have file called tensorflow.py — Ayush Kushwaha
– Ayush Kushwaha, Commented Mar 19, 2019 at 21:15

Himanshu Suthar · Accepted Answer · 2019-04-28 05:56:52Z

13

Change

Import keras.<something>.<something>

to

Import tensorflow.keras.<something>.<something>

where "something" refers to the module you want to import. It worked for me.

answered Apr 28, 2019 at 5:56

Himanshu Suthar

4872 gold badges10 silver badges23 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Ayush Kushwaha Over a year ago

i don't know above answer work or not but i updated my Environment and it worked i think there was an issue related to compatibility.

orangecaterpillar Over a year ago

Worked for me, using tensorflow 2

Amit Rautray · Accepted Answer · 2019-09-04 15:27:22Z

3

Another cause due to which this is happening is that in tensorflow_backend.py

located in : lib/python3.6/site-packages/keras/backend/

uses tf.compat.v1.get_default_graph for obtaining graph

instead of tf.get_default_graph.

By replacing this in the directory this problem can be solved successfully.

answered Sep 4, 2019 at 15:27

Amit Rautray

1767 bronze badges

Comments

jhughs · Accepted Answer · 2019-11-07 15:21:18Z

1

Keras integrated into TensorFlow 2.0

The article below cleared this up for me. Key points are:

Keras is included in the TensorFlow 2.0 package
So no need to install the stand-alone Keras package in your environment
And now the fore-mentioned solutions of using "from tensorflow.keras…" make sense.

After recognizing that and making the change, my code samples work with some minor changes here and there. https://www.pyimagesearch.com/2019/10/21/keras-vs-tf-keras-whats-the-difference-in-tensorflow-2-0/

answered Nov 7, 2019 at 15:21

jhughs

3793 silver badges5 bronze badges

Comments

M.A.S · Accepted Answer · 2019-11-17 20:14:02Z

1

I fixed this problem by replacing tensorflow.keras.* to tensorflow.python.keras.*

Working example:

from tensorflow.python.keras.models import Sequential

answered Nov 17, 2019 at 20:14

M.A.S

341 silver badge2 bronze badges

Comments

lakshmiprabhramesh · Accepted Answer · 2021-06-03 18:26:12Z

1

Two Steps solved this issue for me in Google Colabs

First Step

Change

from keras.something import something

To

from tensorflow.keras.something import something

Second Step

Use

tf.compat.v1.get_default_graph

instead of tf.get_default_graph

Reason

https://www.pyimagesearch.com/2019/10/21/keras-vs-tf-keras-whats-the-difference-in-tensorflow-2-0/

answered Jun 3, 2021 at 18:26

lakshmiprabhramesh

413 bronze badges

Comments

Amit Rautray · Accepted Answer · 2019-09-03 01:47:09Z

0

In my case, replacing

from keras.models import models

with:

from tensorflow.keras.models import models

in my script, fixed this problem.

answered Sep 3, 2019 at 1:47

Amit Rautray

1767 bronze badges

Collectives™ on Stack Overflow

AttributeError: module 'tensorflow' has no attribute 'get_default_graph'

6 Answers 6

2 Comments

Comments

Comments

Comments

Comments

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

6 Answers 6

2 Comments

Comments

Comments

Comments

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related