[BUG] KeyError when running the "Retrain a Model With New Tags" example

[IsaacPushButton]

Describe the bug
I copy pasted the "retrain a model with new tags" example and ran it, and I get the following exception:

Traceback (most recent call last):
  File "example_retrain_tags.py", line 44, in <module>
    logging_path=logging_path,
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/deepparse/parser/address_parser.py", line 719, in retrain
    capturing_context=with_capturing_context,
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/deepparse/parser/address_parser.py", line 1085, in _retrain
    disable_tensorboard=disable_tensorboard,
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/poutyne/framework/model_bundle.py", line 752, in train
    return self._train(self.model.fit_generator, train_generator, valid_generator, **kwargs)
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/poutyne/framework/model_bundle.py", line 913, in _train
    return training_func(*args, initial_epoch=initial_epoch, callbacks=expt_callbacks, **kwargs)
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/poutyne/framework/model.py", line 612, in fit_generator
    self._fit_generator_one_batch_per_step(epoch_iterator, callback_list)
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/poutyne/framework/model.py", line 682, in _fit_generator_one_batch_per_step
    for step, (x, y) in train_step_iterator:
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/poutyne/framework/iterators.py", line 89, in __iter__
    for step, data in _get_step_iterator(self.steps_per_epoch, self.generator):
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/poutyne/framework/iterators.py", line 35, in cycle
    for x in iterable:
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/torch/utils/data/dataloader.py", line 628, in __next__
    data = self._next_data()
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/torch/utils/data/dataloader.py", line 1333, in _next_data
    return self._process_data(data)
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/torch/utils/data/dataloader.py", line 1359, in _process_data
    data.reraise()
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/torch/_utils.py", line 543, in reraise
    raise exception
KeyError: Caught KeyError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 61, in fetch
    return self.collate_fn(data)
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/deepparse/converter/data_processor.py", line 82, in process_for_training
    target_tmp = [self.tags_converter(target) for target in target_list]
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/deepparse/converter/data_processor.py", line 82, in <listcomp>
    target_tmp = [self.tags_converter(target) for target in target_list]
  File "/home/ec2-user/deepparser_au_address/.venv/lib64/python3.7/site-packages/deepparse/converter/target_converter.py", line 24, in __call__
    return self.tags_to_idx[key]
KeyError: 'ATag'

To Reproduce

1. Copy the script at https://github.com/GRAAL-Research/deepparse/blob/main/examples/retrain_with_new_prediction_tags.py into a python file
2. Run it

Desktop (please complete the following information):

Im using deepparse 0.9.4 on amazon linux 2.

Additional context

Looks a lot like this closed issue related to another example script: #117

[github-actions]

Thank you for you interest in improving Deepparse.

[davebulaval]

Error is not the same. I found it. I'm currently working on a fix and adding tests to detect it next time. I will release a new version soon.

[davebulaval]

It is fixed in the new release version 0.9.5.