Getting error!

[kbhartiya]

---

ValueError Traceback (most recent call last)
in ()
----> 1 model = get_model()

in get_model()
15 num_capsule=Num_capsule,
16 dim_capsule=Dim_capsule,
---> 17 routings=Routings)(x)
18
19 capsule = Flatten()(capsule)

/opt/conda/lib/python3.6/site-packages/Keras-2.2.4-py3.6.egg/keras/engine/base_layer.py in call(self, inputs, **kwargs)
455 # Actually call the layer,
456 # collecting output(s), mask(s), and shape(s).
--> 457 output = self.call(inputs, **kwargs)
458 output_mask = self.compute_mask(inputs, previous_mask)
459

in call(self, u_vecs)
70 if i < self.routings - 1:
71 o = K.l2_normalize(o, -1)
---> 72 b = K.batch_dot(o, u_hat_vecs, [2, 3])
73 if K.backend() == 'theano':
74 b = K.sum(b, axis=1)

/opt/conda/lib/python3.6/site-packages/Keras-2.2.4-py3.6.egg/keras/backend/tensorflow_backend.py in batch_dot(x, y, axes)
1222 str(x_shape) + ' and ' + str(y_shape) +
1223 ' with axes=' + str(axes) + '. x.shape[%d] != '
-> 1224 'y.shape[%d] (%d != %d).' % (axes[0], axes[1], d1, d2))
1225
1226 # backup ndims. Need them later.

ValueError: Can not do batch_dot on inputs with shapes (None, 10, 10, 16) and (None, 10, None, 16) with axes=[2, 3]. x.shape[2] != y.shape[3] (10 != 16).

[stefan-it]

@kbhartiya What of version of TensorFlow are you using 🤔 I'm using 1.12rc0 with the latest Keras 2.2.4 version and training starts without problem.

[Rajkumar-Mohan]

@stefan-it I am using keras 2.3.1 and tensorflow 2.1.0. I am too facing the same issue stated above.

Traceback (most recent call last):
File "capsule.py", line 162, in
capsule = Capsule(10, 16, 2, True)(x)
File "C:\Python3\lib\site-packages\keras\backend\tensorflow_backend.py", line 75, in symbolic_fn_wrapper
return func(*args, **kwargs)
File "C:\Python3\lib\site-packages\keras\engine\base_layer.py", line 489, in call
output = self.call(inputs, **kwargs)
File "capsule.py", line 121, in call
b = K.batch_dot(o, hat_inputs, [2, 3])
File "C:\Python3\lib\site-packages\keras\backend\tensorflow_backend.py", line 1499, in batch_dot
'y.shape[%d] (%d != %d).' % (axes[0], axes[1], d1, d2))
ValueError: Can not do batch_dot on inputs with shapes (None, 10, 10, 16) and (None, 10, None, 16) with axes=[2, 3]. x.shape[2] != y.shape[3] (10 != 16).

[Tsai-Cheng-Hong]

Hey guys @Rajkumar-Mohan @kbhartiya
I know how to finish this issue
you should watch this link