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:
try:
return sample.new_inputs(
self._apply_single(sample.inputs, sample.meta))
except Exception as e:
logger.exception(e)
logger.warning(
"There was an unknown error when processing a line image. The line is skipped.\n"
f"The error was caused by the line with meta data: {sample.meta}.\n"
f"Please report this as an issue including the meta data, stack trace, the respective "
f"image file and call.\n"
f"You can ignore this error if it occurs only very rarely, only this particular line will "
f"be skipped.")
return sample.new_invalid()
def apply(self, sample: Sample) -> Sample:
assert (self.data_params.downscale_factor > 0) # Not instantiated yet
codec = self.data_params.codec
# final preparation
text = np.array(
codec.encode(sample.targets) if sample.targets else np.zeros(
(0, ), dtype='int32'))
line = sample.inputs
# gray or binary input, add missing axis
if len(line.shape) == 2:
line = np.expand_dims(line, axis=-1)
if self.mode in {PipelineMode.TRAINING, PipelineMode.EVALUATION
} and not self.is_valid_line(
text,
len(line) // self.data_params.downscale_factor):
# skip longer outputs than inputs (also in evaluation due to loss computation)
logger.warning(
f"Skipping line with longer outputs than inputs (id={sample.meta['id']})"
)
return sample.new_invalid()
if self.mode in {PipelineMode.TRAINING, PipelineMode.EVALUATION
} and len(text) == 0:
logger.warning(
f"Skipping empty line with empty GT (id={sample.meta['id']})")
return sample.new_invalid()
return sample.new_inputs({
'img': line.astype(np.uint8),
'img_len': [len(line)]
}).new_targets({
'gt': text,
'gt_len': [len(text)],
'fold_id': [sample.meta.get('fold_id', -1)]
})
