CTCPostProcessor¶
- class mmocr.models.textrecog.CTCPostProcessor(dictionary, max_seq_len=40, ignore_chars=['padding'], **kwargs)[source]¶
PostProcessor for CTC.
- Parameters
dictionary (Union[mmocr.models.common.dictionary.dictionary.Dictionary, Dict]) –
max_seq_len (int) –
ignore_chars (Sequence[str]) –
- Return type
- get_single_prediction(probs, data_sample)[source]¶
Convert the output probabilities of a single image to index and score.
- Parameters
probs (torch.Tensor) – Character probabilities with shape \((T, C)\).
data_sample (TextRecogDataSample) – Datasample of an image.
- Returns
index and score.
- Return type