DBModuleLoss¶

class mmocr.models.textdet.DBModuleLoss(loss_prob={'type': 'MaskedBalancedBCEWithLogitsLoss'}, loss_thr={'beta': 0, 'type': 'MaskedSmoothL1Loss'}, loss_db={'type': 'MaskedDiceLoss'}, weight_prob=5.0, weight_thr=10.0, shrink_ratio=0.4, thr_min=0.3, thr_max=0.7, min_sidelength=8)[source]¶

The class for implementing DBNet loss.

This is partially adapted from https://github.com/MhLiao/DB.

Parameters

loss_prob (dict) – The loss config for probability map. Defaults to dict(type=’MaskedBalancedBCEWithLogitsLoss’).
loss_thr (dict) – The loss config for threshold map. Defaults to dict(type=’MaskedSmoothL1Loss’, beta=0).
loss_db (dict) – The loss config for binary map. Defaults to dict(type=’MaskedDiceLoss’).
weight_prob (float) – The weight of probability map loss. Denoted as \(\alpha\) in paper. Defaults to 5.
weight_thr (float) – The weight of threshold map loss. Denoted as \(\beta\) in paper. Defaults to 10.
shrink_ratio (float) – The ratio of shrunk text region. Defaults to 0.4.
thr_min (float) – The minimum threshold map value. Defaults to 0.3.
thr_max (float) – The maximum threshold map value. Defaults to 0.7.
min_sidelength (int or float) – The minimum sidelength of the minimum rotated rectangle around any text region. Defaults to 8.

Return type

None

forward(preds, data_samples)[source]¶

Compute DBNet loss.

Parameters

preds (tuple(tensor)) – Raw predictions from model, containing prob_logits, thr_map and binary_map. Each is a tensor of shape \((N, H, W)\).
data_samples (list[TextDetDataSample]) – The data samples.

Returns

The dict for dbnet losses with loss_prob, loss_db and loss_thr.

Return type

results(dict)

get_targets(data_samples)[source]¶

Generate loss targets from data samples.

Parameters: data_samples (list(TextDetDataSample)) – Ground truth data samples.
Returns: A tuple of four tensors as DBNet targets.
Return type: tuple