Hi I would like to propose a better implementation for 'test_indices':

We can remove the unneeded np.array casting:

Cleaner/New:
test_indices = list(set(range(len(texts))) - set(train_indices))

Old:
test_indices = np.array(list(set(range(len(texts))) - set(train_indices)))

What is the desired addition or change?

A parameter check should be added to all bindings that checks for the correct relative input shapes. For example the training data and training labels must have the same number of samples, testing data and training data must have the same number of features etc.

What is the motivation for this feature?

Refer to #2818 for more information and

• What's your use case?

Hi @JavierAntoran @stratisMarkou,

First of all, thanks for making all of this code available - it's been great to look through!

Im currently spending some time trying to work through the Weight Uncertainty in Neural Networks in order to implement Bayes-by-Backprop. I was struggling to understand the difference between your implementation of `Bayes-by-Bac