When I tried to run a sample notebook from MultiFit for German, I got the following error:
Exception Traceback (most recent call last)
~/multifit/notebooks/CLS-DE.ipynb in <module>
----> 1 cls_dataset.load_clas_databunch(bs=exp.finetune_lm.bs).show_batch()
~/multifit/multifit/datasets/dataset.py in load_clas_databunch(self, bs, limit)
224
225 def load_clas_databunch(self, bs, limit=None):
--> 226 vocab = self._load_vocab()
227
228 cls_name = "cls"
~/multifit/multifit/datasets/dataset.py in _load_vocab(self)
220 def _load_vocab(self):
221 if self._vocab is None:
--> 222 self._vocab = self.load_lm_databunch(bs=20, bptt=70).vocab
223 return self._vocab
224
~/multifit/multifit/datasets/dataset.py in load_lm_databunch(self, bs, bptt, limit)
207 bptt=bptt,
208 bs=bs,
--> 209 limit=limit)
210
211 with (self.cache_path / "itos.pkl").open('wb') as f:
~/multifit/multifit/datasets/dataset.py in load_n_cache_databunch(self, name, bunch_class, data_loader, bs, limit, **args)
260 train_df = train_df[:limit]
261 valid_df = valid_df[:limit]
--> 262 databunch = self.databunch_from_df(bunch_class, train_df, valid_df, **args)
263 print("name:", name)
264 databunch.save(name)
~/multifit/multifit/datasets/dataset.py in databunch_from_df(self, bunch_class, train_df, valid_df, **args)
275 mark_fields=True,
276 text_cols=list(train_df.columns.values)[1:],
--> 277 **args)
278 return databunch
279
~/multifit/fastai_contrib/text_data.py in make_data_bunch_from_df(cls, path, train_df, valid_df, tokenizer, vocab, classes, text_cols, label_cols, label_delim, chunksize, max_vocab, min_freq, mark_fields, include_bos, include_eos, processor, **kwargs)
169 else:
170 src = src.label_from_df(cols=label_cols, classes=classes)
--> 171 return src.databunch(**kwargs)
~/miniconda3/lib/python3.7/site-packages/fastai/data_block.py in databunch(self, **kwargs)
744 def databunch(self, **kwargs):
745 "To throw a clear error message when the data wasn't split."
--> 746 raise Exception("Your data isn't split, if you don't want a validation set, please use `split_none`")
747
748 @classmethod
Exception: Your data isn't split, if you don't want a validation set, please use `split_none`