File size: 9,246 Bytes
c59c099 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 |
import torch
from torch import nn as nn
from torch.nn import functional as F
from basicsr.archs.vgg_arch import VGGFeatureExtractor
from basicsr.utils.registry import LOSS_REGISTRY
from .loss_util import weighted_loss
_reduction_modes = ['none', 'mean', 'sum']
@weighted_loss
def l1_loss(pred, target):
return F.l1_loss(pred, target, reduction='none')
@weighted_loss
def mse_loss(pred, target):
return F.mse_loss(pred, target, reduction='none')
@weighted_loss
def charbonnier_loss(pred, target, eps=1e-12):
return torch.sqrt((pred - target)**2 + eps)
@LOSS_REGISTRY.register()
class L1Loss(nn.Module):
"""L1 (mean absolute error, MAE) loss.
Args:
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'.
"""
def __init__(self, loss_weight=1.0, reduction='mean'):
super(L1Loss, self).__init__()
if reduction not in ['none', 'mean', 'sum']:
raise ValueError(f'Unsupported reduction mode: {reduction}. Supported ones are: {_reduction_modes}')
self.loss_weight = loss_weight
self.reduction = reduction
def forward(self, pred, target, weight=None, **kwargs):
"""
Args:
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.
"""
return self.loss_weight * l1_loss(pred, target, weight, reduction=self.reduction)
@LOSS_REGISTRY.register()
class MSELoss(nn.Module):
"""MSE (L2) loss.
Args:
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'.
"""
def __init__(self, loss_weight=1.0, reduction='mean'):
super(MSELoss, self).__init__()
if reduction not in ['none', 'mean', 'sum']:
raise ValueError(f'Unsupported reduction mode: {reduction}. Supported ones are: {_reduction_modes}')
self.loss_weight = loss_weight
self.reduction = reduction
def forward(self, pred, target, weight=None, **kwargs):
"""
Args:
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.
"""
return self.loss_weight * mse_loss(pred, target, weight, reduction=self.reduction)
@LOSS_REGISTRY.register()
class CharbonnierLoss(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".
Args:
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'.
eps (float): A value used to control the curvature near zero. Default: 1e-12.
"""
def __init__(self, loss_weight=1.0, reduction='mean', eps=1e-12):
super(CharbonnierLoss, self).__init__()
if reduction not in ['none', 'mean', 'sum']:
raise ValueError(f'Unsupported reduction mode: {reduction}. Supported ones are: {_reduction_modes}')
self.loss_weight = loss_weight
self.reduction = reduction
self.eps = eps
def forward(self, pred, target, weight=None, **kwargs):
"""
Args:
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.
"""
return self.loss_weight * charbonnier_loss(pred, target, weight, eps=self.eps, reduction=self.reduction)
@LOSS_REGISTRY.register()
class WeightedTVLoss(L1Loss):
"""Weighted TV loss.
Args:
loss_weight (float): Loss weight. Default: 1.0.
"""
def __init__(self, loss_weight=1.0, reduction='mean'):
if reduction not in ['mean', 'sum']:
raise ValueError(f'Unsupported reduction mode: {reduction}. Supported ones are: mean | sum')
super(WeightedTVLoss, self).__init__(loss_weight=loss_weight, reduction=reduction)
def forward(self, pred, weight=None):
if weight is None:
y_weight = None
x_weight = None
else:
y_weight = weight[:, :, :-1, :]
x_weight = weight[:, :, :, :-1]
y_diff = super().forward(pred[:, :, :-1, :], pred[:, :, 1:, :], weight=y_weight)
x_diff = super().forward(pred[:, :, :, :-1], pred[:, :, :, 1:], weight=x_weight)
loss = x_diff + y_diff
return loss
@LOSS_REGISTRY.register()
class PerceptualLoss(nn.Module):
"""Perceptual loss with commonly used style loss.
Args:
layer_weights (dict): The weight for each layer of vgg feature.
Here is an example: {'conv5_4': 1.}, which means the conv5_4
feature layer (before relu5_4) will be extracted with weight
1.0 in calculating losses.
vgg_type (str): The type of vgg network used as feature extractor.
Default: 'vgg19'.
use_input_norm (bool): If True, normalize the input image in vgg.
Default: True.
range_norm (bool): If True, norm images with range [-1, 1] to [0, 1].
Default: False.
perceptual_weight (float): If `perceptual_weight > 0`, the perceptual
loss will be calculated and the loss will multiplied by the
weight. Default: 1.0.
style_weight (float): If `style_weight > 0`, the style loss will be
calculated and the loss will multiplied by the weight.
Default: 0.
criterion (str): Criterion used for perceptual loss. Default: 'l1'.
"""
def __init__(self,
layer_weights,
vgg_type='vgg19',
use_input_norm=True,
range_norm=False,
perceptual_weight=1.0,
style_weight=0.,
criterion='l1'):
super(PerceptualLoss, self).__init__()
self.perceptual_weight = perceptual_weight
self.style_weight = style_weight
self.layer_weights = layer_weights
self.vgg = VGGFeatureExtractor(
layer_name_list=list(layer_weights.keys()),
vgg_type=vgg_type,
use_input_norm=use_input_norm,
range_norm=range_norm)
self.criterion_type = criterion
if self.criterion_type == 'l1':
self.criterion = torch.nn.L1Loss()
elif self.criterion_type == 'l2':
self.criterion = torch.nn.MSELoss()
elif self.criterion_type == 'fro':
self.criterion = None
else:
raise NotImplementedError(f'{criterion} criterion has not been supported.')
def forward(self, x, gt):
"""Forward function.
Args:
x (Tensor): Input tensor with shape (n, c, h, w).
gt (Tensor): Ground-truth tensor with shape (n, c, h, w).
Returns:
Tensor: Forward results.
"""
# extract vgg features
x_features = self.vgg(x)
gt_features = self.vgg(gt.detach())
# calculate perceptual loss
if self.perceptual_weight > 0:
percep_loss = 0
for k in x_features.keys():
if self.criterion_type == 'fro':
percep_loss += torch.norm(x_features[k] - gt_features[k], p='fro') * self.layer_weights[k]
else:
percep_loss += self.criterion(x_features[k], gt_features[k]) * self.layer_weights[k]
percep_loss *= self.perceptual_weight
else:
percep_loss = None
# calculate style loss
if self.style_weight > 0:
style_loss = 0
for k in x_features.keys():
if self.criterion_type == 'fro':
style_loss += torch.norm(
self._gram_mat(x_features[k]) - self._gram_mat(gt_features[k]), p='fro') * self.layer_weights[k]
else:
style_loss += self.criterion(self._gram_mat(x_features[k]), self._gram_mat(
gt_features[k])) * self.layer_weights[k]
style_loss *= self.style_weight
else:
style_loss = None
return percep_loss, style_loss
def _gram_mat(self, x):
"""Calculate Gram matrix.
Args:
x (torch.Tensor): Tensor with shape of (n, c, h, w).
Returns:
torch.Tensor: Gram matrix.
"""
n, c, h, w = x.size()
features = x.view(n, c, w * h)
features_t = features.transpose(1, 2)
gram = features.bmm(features_t) / (c * h * w)
return gram
|