Where is keras_tokenizer.json supposed to come from for clinc_intent.py?

[jayargo]

Hi There,

I'm trying to do a simple smoke test of uncertainty-baselines and thought I'd use baselines/clinc_intent/deterministic.py . However, I'm not entirely sure I understand how to run this example. In particular where is keras_tokenizer.json supposed to come from?

Here's what I've tried:
pip install --upgrade pip setuptools
pip install --editable .[tensorflow,models,datasets]

tfds build --data_dir tensorflow_datasets clinc_oos

python baselines/clinc_intent/deterministic.py
--data_dir=tensorflow_datasets/clinc_oos
--bert_dir=models/uncased_L-12_H-768_A-12
--output_dir=/tmp/model
--use_gpu=True
--num_cores=1

Which generates this error:
File "/mnt/shared_ad2_mt1/jpeck/src/uncertainty-baselines/venv/lib64/python3.6/site-packages/tensorflow/python/lib/io/file_io.py", line 80, in _preread_check
compat.path_to_str(self.__name), 1024 * 512)
tensorflow.python.framework.errors_impl.NotFoundError: tensorflow_datasets/clinc_oos/keras_tokenizer.json; No such file or directory