LatentCrossCorrelationHead

class mmpretrain.models.heads.LatentCrossCorrelationHead(in_channels, loss, init_cfg=None)

Head for latent feature cross correlation.

Part of the code is borrowed from script.

参数:

• in_channels (int) – Number of input channels.

• loss (dict) – Config dict for module of loss functions.

• init_cfg (dict or List[dict], optional) – Initialization config dict. Defaults to None.

loss(input, target)

Forward head.

参数:

• input (torch.Tensor) – NxC input features.

• target (torch.Tensor) – NxC target features.

返回:

The cross correlation loss.

返回类型:

torch.Tensor