AttributeError: 'int' object has no attribute 'value'

[gunju]

Hi, I am facing below issue:

AttributeErrorTraceback (most recent call last)
in ()
1 # Layer 1: Primary Capsule: Conv cap with routing 1
2 primary_caps = ConvCapsuleLayer(kernel_size=5, num_capsule=2, num_atoms=16, strides=2, padding='same',
----> 3 routings=1, name='primarycaps')(conv1_reshaped)

/home/ubuntu/anaconda3/envs/tensorflow2_p27/lib/python2.7/site-packages/keras/backend/tensorflow_backend.pyc in symbolic_fn_wrapper(*args, **kwargs)
73 if _SYMBOLIC_SCOPE.value:
74 with get_graph().as_default():
---> 75 return func(*args, **kwargs)
76 else:
77 return func(*args, **kwargs)

/home/ubuntu/anaconda3/envs/tensorflow2_p27/lib/python2.7/site-packages/keras/engine/base_layer.pyc in call(self, inputs, **kwargs)
487 # Actually call the layer,
488 # collecting output(s), mask(s), and shape(s).
--> 489 output = self.call(inputs, **kwargs)
490 output_mask = self.compute_mask(inputs, previous_mask)
491

capsule_layers.py in call(self, input_tensor, training)
138 votes = K.reshape(conv, [input_shape[1], input_shape[0], votes_shape[1], votes_shape[2],
139 self.num_capsule, self.num_atoms])
--> 140 votes.set_shape((None, self.input_num_capsule, conv_height.value, conv_width.value,
141 self.num_capsule, self.num_atoms))
142

AttributeError: 'int' object has no attribute 'value'

I am using python 3.6.5, keras 2.3.0 and tensorflow-gpu 2.0.0.

Shall I remove the value section and keep directly the values? I am getting values directly for conv network.