Shortcuts

iTPN

class mmpretrain.models.selfsup.iTPN(backbone, neck=None, head=None, target_generator=None, pretrained=None, data_preprocessor=None, init_cfg=None)[source]

iTPN.

Implementation of iTPN: Integrally Pre-Trained Transformer Pyramid Networks.

loss(inputs, data_samples, **kwargs)[source]

The forward function in training.

Parameters:
  • inputs (torch.Tensor) – The input images.

  • data_samples (List[DataSample]) – All elements required during the forward function.

Returns:

A dictionary of loss components.

Return type:

Dict[str, torch.Tensor]