AttributeError: 'Conv2D' object has no attribute 'kernel' on running MNIST Keras pruning Example

[rishab-sharma]

When I am trying to run the MNIST Example of keras pruning Link, I get the following Traceback.
Tensorflow Version:
Name: tensorflow Version: 2.0.0a0

Traceback

--> 156   layerwise_model = build_layerwise_model(input_shape, **pruning_params)
    157   sequential_model = build_sequential_model(input_shape)
    158   sequential_model = prune.prune_low_magnitude(

<ipython-input-9-8bf64bf9319d> in build_layerwise_model(input_shape, **pruning_params)
     73       l.Dropout(0.4),
     74       prune.prune_low_magnitude(
---> 75           l.Dense(num_classes, activation='softmax'), **pruning_params)
     76   ])
     77 

/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
    454     self._setattr_tracking = False  # pylint: disable=protected-access
    455     try:
--> 456       result = method(self, *args, **kwargs)
    457     finally:
    458       self._setattr_tracking = previous_value  # pylint: disable=protected-access

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/sequential.py in __init__(self, layers, name)
    106     if layers:
    107       for layer in layers:
--> 108         self.add(layer)
    109 
    110   @property

/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
    454     self._setattr_tracking = False  # pylint: disable=protected-access
    455     try:
--> 456       result = method(self, *args, **kwargs)
    457     finally:
    458       self._setattr_tracking = previous_value  # pylint: disable=protected-access

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/sequential.py in add(self, layer)
    167           # and create the node connecting the current layer
    168           # to the input layer we just created.
--> 169           layer(x)
    170           set_inputs = True
    171 

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, inputs, *args, **kwargs)
    592           # Build layer if applicable (if the `build` method has been
    593           # overridden).
--> 594           self._maybe_build(inputs)
    595           # Explicitly pass the learning phase placeholder to `call` if
    596           # the `training` argument was left unspecified by the user.

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in _maybe_build(self, inputs)
   1711     # Only call `build` if the user has manually overridden the build method.
   1712     if not hasattr(self.build, '_is_default'):
-> 1713       self.build(input_shapes)
   1714     # We must set self.built since user defined build functions are not
   1715     # constrained to set self.built.

/usr/local/lib/python3.6/dist-packages/tensorflow_model_optimization/python/core/sparsity/keras/pruning_wrapper.py in build(self, input_shape)
    173     weight_vars, mask_vars, threshold_vars = [], [], []
    174 
--> 175     self.prunable_weights = self.layer.get_prunable_weights()
    176 
    177     # For each of the prunable weights, add mask and threshold variables

/usr/local/lib/python3.6/dist-packages/tensorflow_model_optimization/python/core/sparsity/keras/prune_registry.py in get_prunable_weights()
    167 
    168     def get_prunable_weights():
--> 169       return [getattr(layer, weight) for weight in cls._weight_names(layer)]
    170 
    171     def get_prunable_weights_rnn():  # pylint: disable=missing-docstring

/usr/local/lib/python3.6/dist-packages/tensorflow_model_optimization/python/core/sparsity/keras/prune_registry.py in <listcomp>(.0)
    167 
    168     def get_prunable_weights():
--> 169       return [getattr(layer, weight) for weight in cls._weight_names(layer)]
    170 
    171     def get_prunable_weights_rnn():  # pylint: disable=missing-docstring

AttributeError: 'Conv2D' object has no attribute 'kernel'

I am not using absl-py to run the main(), because I am using colab, therefore, I have also commented out the eager execution line.

Can anyone please help me this, where I am going wrong, or is this a bug?

[rishab-sharma]

Going through this, solved the issue

! pip uninstall -y tensorflow
! pip uninstall -y tf-nightly
! pip install -U tf-nightly-gpu

! pip install tensorflow-model-optimization

import tensorflow as tf
tf.enable_eager_execution()