def to_raw_input_dataset(self,
processes=1,
progress_bar=False,
text_only=False) -> RawInputDataset:
print("Preloading dataset type {} with size {}".format(
self.dataset.mode, len(self)))
prev = self._generate_only_non_augmented.value
self._generate_only_non_augmented.value = True
datas, texts, params = zip(*list(
tqdm_wrapper(self.generator(epochs=1, text_only=text_only),
desc="Preloading data",
total=len(self.dataset),
progress_bar=progress_bar)))
preloaded_datas, preloaded_texts, preloaded_params = datas, texts, params
self._generate_only_non_augmented.value = prev
if self.dataset.mode == DataSetMode.TRAIN and self.data_augmentation_amount > 0:
abs_n_augs = int(self.data_augmentation_amount
) if self.data_augmentation_amount >= 1 else int(
self.data_augmentation_amount * len(self))
preloaded_datas, preloaded_texts \
= self.data_augmenter.augment_datas(list(datas), list(texts), n_augmentations=abs_n_augs,
processes=processes, progress_bar=progress_bar)
return RawInputDataset(self.mode, preloaded_datas, preloaded_texts,
preloaded_params)
def _compute_current_cer_on_validation_set(self, count):
def generate_cer():
it = iter(self.data_gen)
for _ in range(count):
yield np.mean(self.predict_func(next(it))[0])
return np.mean([cer for cer in tqdm_wrapper(generate_cer(), total=count, progress_bar=self.progress_bar, desc="Early stopping") if np.isfinite(cer)])
def from_input_dataset(input_dataset: List[InputDataset], whitelist=set(), progress_bar=False):
chars = set(whitelist)
for ds in input_dataset:
if not ds:
continue
for text in tqdm_wrapper(ds.text_generator(), total=len(ds), desc="Computing codec", progress_bar=progress_bar):
for c in text:
chars.add(c)
return Codec(sorted(list(chars)))
def from_input_dataset(input_dataset: List[InputDataset],
whitelist=None,
progress_bar=False):
chars = set() if whitelist is None else set(whitelist)
for ds in input_dataset:
if not ds:
continue
for text in tqdm_wrapper(ds.text_generator(),
total=len(ds),
desc="Computing codec",
progress_bar=progress_bar):
for c in text:
chars.add(c)
return Codec(sorted(list(chars)))