RuntimeError: The layer has never been called and thus has no defined output shape.

[PratsBhatt]

Please make sure that this is a bug. As per our
GitHub Policy,
we only address code/doc bugs, performance issues, feature requests and
build/installation issues on GitHub. tag:bug_template

System information

• Have I written custom code (as opposed to using a stock example script provided in TensorFlow):
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 18.04
• Mobile device (e.g. iPhone 8, Pixel 2, Samsung Galaxy) if the issue happens on mobile device:
• TensorFlow installed from (source or binary): Used Google Colab
• TensorFlow version (use command below): 2.3.0
• Python version: 3.6.9
• Bazel version (if compiling from source):
• GCC/Compiler version (if compiling from source):
• CUDA/cuDNN version: Doesn't matter
• GPU model and memory: Doesn't matter

You can collect some of this information using our environment capture
script
You can also obtain the TensorFlow version with:

1. TF 1.0: python -c "import tensorflow as tf; print(tf.GIT_VERSION, tf.VERSION)"
2. TF 2.0: python -c "import tensorflow as tf; print(tf.version.GIT_VERSION, tf.version.VERSION)"

Describe the current behavior
I used to run below mentioned code in the tensorflow version 1.15 but since the time I have upgraded it fails to run.
I have already gone through similar bugs, but they all mention that I should have provided the input shape, I have done that, so I am not sure where the problem lies.

model = DenseNet121(input_shape=(810, 1440, 3),
                                         include_top=False,
                                         weights='imagenet'
                                         )

depth = model.get_output_shape_at(0)[-1]

Describe the expected behavior
Expected behaviour should be that I should be able to get the output shape of the last layer.

Standalone code to reproduce the issue
Provide a reproducible test case that is the bare minimum necessary to generate
the problem. If possible, please share a link to Colab/Jupyter/any notebook.

Everyone can recreate the issue using the below colab link.
https://colab.research.google.com/drive/1TPYkETG8szsCvut6SdzY345jEnqOrgsg?usp=sharing

Other info / logs Include any logs or source code that would be helpful to
diagnose the problem. If including tracebacks, please include the full
traceback. Large logs and files should be attached.

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-4-c67805c58fe0> in <module>()
----> 1 depth = model.get_output_shape_at(0)[-1]

1 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in get_output_shape_at(self, node_index)
   2028     """
   2029     return self._get_node_attribute_at_index(node_index, 'output_shapes',
-> 2030                                              'output shape')
   2031 
   2032   @doc_controls.do_not_doc_inheritable

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in _get_node_attribute_at_index(self, node_index, attr, attr_name)
   2601     if not self._inbound_nodes:
   2602       raise RuntimeError('The layer has never been called '
-> 2603                          'and thus has no defined ' + attr_name + '.')
   2604     if not len(self._inbound_nodes) > node_index:
   2605       raise ValueError('Asked to get ' + attr_name + ' at node ' +

RuntimeError: The layer has never been called and thus has no defined output shape.

[bhack]

Can you unlock the Colab?

[PratsBhatt]

Yes, I just unlocked it for everyone - https://colab.research.google.com/drive/1TPYkETG8szsCvut6SdzY345jEnqOrgsg?usp=sharing

[bhack]

You need to call the model with an input:
E.g.

model(tf.keras.Input((810, 1440, 3)))
depth = model.get_output_shape_at(0)

[PratsBhatt]

But, if you have observed, when I am initializing the densenet model, I am providing the input shape.

Then why do I need to provide it two times?

[bhack]

The layer need to be called. See the difference between call and build https://keras.io/api/layers/base_layer/

[google-ml-butler]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you.

[google-ml-butler]

Closing as stale. Please reopen if you'd like to work on this further.

[google-ml-butler]

Are you satisfied with the resolution of your issue?
Yes
No