Make sure validation batch size smaller than validation dataset

By default the validation batch size is the same as the training batch size, but sometimes there are not many validation images and this gives an error when the batch size is larger than the number of validation images. I think we should add a check to make sure this does not happen.

Here is what I suggest. Add an extra value in the `__init__` for the val_batch_size. If the batch size is smaller than the size of the validation dataset, then this value is the batch size. Otherwise we take something like half the size of the dataset. This will require to add the batch size as an argument in the `_get_dataset` method and use the correct one when we get a dataset.

Start by reading the __init__ method and the _get_dataset method mentioned in the issue, then inspect the open pull request linked to this issue to understand the work already underway. Done means validation dataset creation no longer fails when the validation set is smaller than the training batch size, with the selected validation batch size used consistently.

Written by the indexing model from the issue text.