def apply(self, sample: Sample) -> Sample:
assert self.data_params.downscale_factor > 0 # Not instantiated yet
codec = self.data_params.codec
# final preparation
if self.mode in {PipelineMode.TRAINING, PipelineMode.EVALUATION}:
text = np.array(codec.encode(sample.targets) if sample.targets else np.zeros((0,), dtype="int32"))
else:
text = None
line = sample.inputs
# gray or binary input, add missing axis
if len(line.shape) == 2:
line = np.expand_dims(line, axis=-1)
# Validate if the line is valid for training
if not self.is_valid_line(
text, len(line) // self.data_params.downscale_factor, len(line), sample.meta.get("id", "Unknown Sample ID")
):
return sample.new_invalid()
if text is not None:
sample = sample.new_targets(
{
"gt": np.asarray(text),
"gt_len": np.asarray([len(text)]),
"fold_id": np.asarray([sample.meta.get("fold_id", -1)]),
}
)
return sample.new_inputs({"img": line.astype(np.uint8), "img_len": np.asarray([len(line)])})
def apply(self, sample: Sample) -> Sample:
targets: str = sample.targets
outputs: str = sample.outputs
meta = sample.meta
if isinstance(outputs, Prediction):
prediction: Prediction = outputs
prediction.sentence = self._apply_single(prediction.sentence, meta)
return sample
elif isinstance(targets, dict) and "sentence" in targets:
targets["sentence"] = self._apply_single(targets["sentence"], meta)
return sample
elif isinstance(outputs, dict) and "sentence" in outputs:
outputs["sentence"] = self._apply_single(outputs["sentence"], meta)
return sample
else:
if targets:
sample = sample.new_targets(self._apply_single(targets, meta))
if outputs:
sample = sample.new_outputs(self._apply_single(outputs, meta))
return sample
