Skip to content

Instantly share code, notes, and snippets.

@JacopoMangiavacchi
Forked from alper111/vgg_perceptual_loss.py
Last active January 17, 2022 17:14
Show Gist options
  • Save JacopoMangiavacchi/99bb1a4eb0de69d4d861b7bf752f0ed4 to your computer and use it in GitHub Desktop.
Save JacopoMangiavacchi/99bb1a4eb0de69d4d861b7bf752f0ed4 to your computer and use it in GitHub Desktop.
PyTorch implementation of VGG perceptual loss
import torch
import torchvision
class VGGPerceptualLoss(torch.nn.Module):
def __init__(self, resize=True):
super(VGGPerceptualLoss, self).__init__()
blocks = []
blocks.append(torchvision.models.vgg16(pretrained=True).features[:4].eval())
blocks.append(torchvision.models.vgg16(pretrained=True).features[4:9].eval())
blocks.append(torchvision.models.vgg16(pretrained=True).features[9:16].eval())
blocks.append(torchvision.models.vgg16(pretrained=True).features[16:23].eval())
for bl in blocks:
for p in bl.parameters():
p.requires_grad = False
self.blocks = torch.nn.ModuleList(blocks)
self.transform = torch.nn.functional.interpolate
self.resize = resize
self.register_buffer("mean", torch.tensor([0.485, 0.456, 0.406]).view(1, 3, 1, 1))
self.register_buffer("std", torch.tensor([0.229, 0.224, 0.225]).view(1, 3, 1, 1))
def forward(self, input, target, feature_layers_weight=[1, 1, 1, 1], style_layers_weight=[1, 1, 1, 1]):
if input.shape[1] != 3:
input = input.repeat(1, 3, 1, 1)
target = target.repeat(1, 3, 1, 1)
input = (input-self.mean) / self.std
target = (target-self.mean) / self.std
if self.resize:
input = self.transform(input, mode='bilinear', size=(224, 224), align_corners=False)
target = self.transform(target, mode='bilinear', size=(224, 224), align_corners=False)
loss = 0.0
x = input
y = target
for i, block in enumerate(self.blocks):
x = block(x)
y = block(y)
if feature_layers_weight[i] > 0:
feature_weight = feature_layers_weight[i]
loss += feature_weight * torch.nn.functional.l1_loss(x, y)
if style_layers_weight[i] > 0:
act_x = x.reshape(x.shape[0], x.shape[1], -1)
act_y = y.reshape(y.shape[0], y.shape[1], -1)
gram_x = act_x @ act_x.permute(0, 2, 1)
gram_y = act_y @ act_y.permute(0, 2, 1)
style_weight = style_layers_weight[i]
loss += style_weight * torch.nn.functional.l1_loss(gram_x, gram_y)
return loss
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment