mmagic.models.losses.pixelwise_loss

Module Contents

Classes

L1Loss	L1 (mean absolute error, MAE) loss.
MSELoss	MSE (L2) loss.
CharbonnierLoss	Charbonnier loss (one variant of Robust L1Loss, a differentiable variant
MaskedTVLoss	Masked TV loss.
PSNRLoss	PSNR Loss in "HINet: Half Instance Normalization Network for Image

Functions

l1_loss(→ torch.Tensor)	L1 loss.
mse_loss(→ torch.Tensor)	MSE loss.
charbonnier_loss(→ torch.Tensor)	Charbonnier loss.
tv_loss(→ torch.Tensor)	L2 total variation loss, as in Mahendran et al.

Attributes

_reduction_modes

mmagic.models.losses.pixelwise_loss._reduction_modes = ['none', 'mean', 'sum']

mmagic.models.losses.pixelwise_loss.l1_loss(pred: torch.Tensor, target: torch.Tensor) → torch.Tensor

L1 loss.

Parameters

• pred (Tensor) – Prediction Tensor with shape (n, c, h, w).

• target ([type]) – Target Tensor with shape (n, c, h, w).

Returns

Calculated L1 loss.

Return type

Tensor

mmagic.models.losses.pixelwise_loss.mse_loss(pred: torch.Tensor, target: torch.Tensor) → torch.Tensor

MSE loss.

Parameters

• pred (Tensor) – Prediction Tensor with shape (n, c, h, w).

• target ([type]) – Target Tensor with shape (n, c, h, w).

Returns

Calculated MSE loss.

Return type

Tensor

mmagic.models.losses.pixelwise_loss.charbonnier_loss(pred: torch.Tensor, target: torch.Tensor, eps: float = 1e-12) → torch.Tensor

Charbonnier loss.

Parameters

• pred (Tensor) – Prediction Tensor with shape (n, c, h, w).

• target ([type]) – Target Tensor with shape (n, c, h, w).

• eps (float) – A value used to control the curvature near zero. Default: 1e-12.

Returns

Calculated Charbonnier loss.

Return type

Tensor

mmagic.models.losses.pixelwise_loss.tv_loss(input: torch.Tensor) → torch.Tensor

L2 total variation loss, as in Mahendran et al.

class mmagic.models.losses.pixelwise_loss.L1Loss(loss_weight: float = 1.0, reduction: str = 'mean', sample_wise: bool = False)

Bases: torch.nn.Module

L1 (mean absolute error, MAE) loss.

Parameters

• loss_weight (float) – Loss weight for L1 loss. Default: 1.0.

• reduction (str) – Specifies the reduction to apply to the output. Supported choices are ‘none’ | ‘mean’ | ‘sum’. Default: ‘mean’.

• sample_wise (bool) – Whether calculate the loss sample-wise. This argument only takes effect when reduction is ‘mean’ and weight (argument of forward()) is not None. It will first reduce loss with ‘mean’ per-sample, and then it means over all the samples. Default: False.

forward(pred: torch.Tensor, target: torch.Tensor, weight: Optional[torch.Tensor] = None, **kwargs) → torch.Tensor

Forward Function.

Parameters

• pred (Tensor) – of shape (N, C, H, W). Predicted tensor.

• target (Tensor) – of shape (N, C, H, W). Ground truth tensor.

• weight (Tensor, optional) – of shape (N, C, H, W). Element-wise weights. Default: None.

class mmagic.models.losses.pixelwise_loss.MSELoss(loss_weight: float = 1.0, reduction: str = 'mean', sample_wise: bool = False)

Bases: torch.nn.Module

MSE (L2) loss.

Parameters

• loss_weight (float) – Loss weight for MSE loss. Default: 1.0.

• reduction (str) – Specifies the reduction to apply to the output. Supported choices are ‘none’ | ‘mean’ | ‘sum’. Default: ‘mean’.

• sample_wise (bool) – Whether calculate the loss sample-wise. This argument only takes effect when reduction is ‘mean’ and weight (argument of forward()) is not None. It will first reduces loss with ‘mean’ per-sample, and then it means over all the samples. Default: False.

forward(pred: torch.Tensor, target: torch.Tensor, weight: Optional[torch.Tensor] = None, **kwargs) → torch.Tensor

Forward Function.

Parameters

• pred (Tensor) – of shape (N, C, H, W). Predicted tensor.

• target (Tensor) – of shape (N, C, H, W). Ground truth tensor.

• weight (Tensor, optional) – of shape (N, C, H, W). Element-wise weights. Default: None.

class mmagic.models.losses.pixelwise_loss.CharbonnierLoss(loss_weight: float = 1.0, reduction: str = 'mean', sample_wise: bool = False, eps: float = 1e-12)

Bases: torch.nn.Module

Charbonnier loss (one variant of Robust L1Loss, a differentiable variant of L1Loss).

Described in “Deep Laplacian Pyramid Networks for Fast and Accurate

Super-Resolution”.

Parameters

• loss_weight (float) – Loss weight for L1 loss. Default: 1.0.

• reduction (str) – Specifies the reduction to apply to the output. Supported choices are ‘none’ | ‘mean’ | ‘sum’. Default: ‘mean’.

• sample_wise (bool) – Whether calculate the loss sample-wise. This argument only takes effect when reduction is ‘mean’ and weight (argument of forward()) is not None. It will first reduces loss with ‘mean’ per-sample, and then it means over all the samples. Default: False.

• eps (float) – A value used to control the curvature near zero. Default: 1e-12.

forward(pred: torch.Tensor, target: torch.Tensor, weight: Optional[torch.Tensor] = None, **kwargs) → torch.Tensor

Forward Function.

Parameters

• pred (Tensor) – of shape (N, C, H, W). Predicted tensor.

• target (Tensor) – of shape (N, C, H, W). Ground truth tensor.

• weight (Tensor, optional) – of shape (N, C, H, W). Element-wise weights. Default: None.

class mmagic.models.losses.pixelwise_loss.MaskedTVLoss(loss_weight: float = 1.0)

Bases: L1Loss

Masked TV loss.

Parameters

loss_weight (float, optional) – Loss weight. Defaults to 1.0.

forward(pred: torch.Tensor, mask: Optional[torch.Tensor] = None) → torch.Tensor

Forward function.

Parameters

• pred (torch.Tensor) – Tensor with shape of (n, c, h, w).

• mask (torch.Tensor, optional) – Tensor with shape of (n, 1, h, w). Defaults to None.

Returns

[description]

Return type

[type]

class mmagic.models.losses.pixelwise_loss.PSNRLoss(loss_weight: float = 1.0, toY: bool = False)

Bases: torch.nn.Module

PSNR Loss in “HINet: Half Instance Normalization Network for Image Restoration”.

Parameters

• loss_weight (float, optional) – Loss weight. Defaults to 1.0.

• reduction – reduction for PSNR. Can only be mean here.

• toY – change to calculate the PSNR of Y channel in YCbCr format

forward(pred: torch.Tensor, target: torch.Tensor) → torch.Tensor