ABIModuleLoss

class mmocr.models.textrecog.ABIModuleLoss(dictionary, max_seq_len=40, letter_case='unchanged', weight_vis=1.0, weight_lang=1.0, weight_fusion=1.0, **kwargs)

Implementation of ABINet multiloss that allows mixing different types of losses with weights.

参数

• 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’.

• weight_vis (float or int) – The weight of vision decoder loss. Defaults to 1.0.

• weight_dec (float or int) – The weight of language decoder loss. Defaults to 1.0.

• weight_fusion (float or int) – The weight of fuser (aligner) loss. Defaults to 1.0.

• weight_lang (Union[float, int]) –

返回类型

None

forward(outputs, data_samples)

参数

• outputs (dict) – The output dictionary with at least one of out_vis, out_langs and out_fusers specified.

• data_samples (list[TextRecogDataSample]) – List of TextRecogDataSample which are processed by get_target.

返回

A loss dictionary with loss_visual, loss_lang and loss_fusion. Each should either be the loss tensor or None if the output of its corresponding module is not given.

返回类型

dict