BaseTextRecogModuleLoss

class mmocr.models.textrecog.BaseTextRecogModuleLoss(dictionary, max_seq_len=40, letter_case='unchanged', pad_with='auto', **kwargs)

Base recognition loss.

Parameters

• dictionary (dict or Dictionary) – The config for Dictionary or the instance of Dictionary.

• max_seq_len (int) – Maximum sequence length. The sequence is usually generated from decoder. Defaults to 40.

• letter_case (str) – There are three options to alter the letter cases of gt texts: - unchanged: Do not change gt texts. - upper: Convert gt texts into uppercase characters. - lower: Convert gt texts into lowercase characters. Usually, it only works for English characters. Defaults to ‘unchanged’.

• pad_with (str) –

  The padding strategy for gt_text.padded_indexes. Defaults to ‘auto’. Options are: - ‘auto’: Use dictionary.padding_idx to pad gt texts, or

  dictionary.end_idx if dictionary.padding_idx is None.

  • ’padding’: Always use dictionary.padding_idx to pad gt texts.

  • ’end’: Always use dictionary.end_idx to pad gt texts.

  • ’none’: Do not pad gt texts.

Return type

None

get_targets(data_samples)

Target generator.

Parameters

data_samples (list[TextRecogDataSample]) – It usually includes gt_text information.

Returns

Updated data_samples. Two keys will be added to data_sample:

• indexes (torch.LongTensor): Character indexes representing gt texts. All special tokens are excluded, except for UKN.

• padded_indexes (torch.LongTensor): Character indexes representing gt texts with BOS and EOS if applicable, following several padding indexes until the length reaches max_seq_len. In particular, if pad_with='none', no padding will be applied.

Return type

list[TextRecogDataSample]