`mmagic.models.losses.feature_loss`¶

Module Contents¶

`LightCNNFeature`	Feature of LightCNN.
`LightCNNFeatureLoss`	Feature loss of DICGAN, based on LightCNN.

class mmagic.models.losses.feature_loss.LightCNNFeature[source]¶

Bases: torch.nn.Module

Feature of LightCNN.

It is used to train DICGAN.

forward(x: torch.Tensor) → torch.Tensor[source]¶

Forward function.

init_weights(pretrained: Optional[str] = None, strict: bool = True) → None[source]¶

Init weights for models.

Parameters

pretrained (str, optional) – Path for pretrained weights. If given None, pretrained weights will not be loaded. Defaults to None.
strict (boo, optional) – Whether strictly load the pretrained model. Defaults to True.

class mmagic.models.losses.feature_loss.LightCNNFeatureLoss(pretrained: str, loss_weight: float = 1.0, criterion: str = 'l1')[source]¶

Bases: torch.nn.Module

Feature loss of DICGAN, based on LightCNN.

Parameters

pretrained (str) – Path for pretrained weights.
loss_weight (float) – Loss weight. Default: 1.0.
criterion (str) – Criterion type. Options are ‘l1’ and ‘mse’. Default: ‘l1’.

forward(pred: torch.Tensor, gt: torch.Tensor) → torch.Tensor[source]¶

Forward function.

Parameters

Returns

Forward results.

Return type

Tensor