File size: 2,304 Bytes
87ef7b5 | 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 | # ==================================================================
# LEARNED PERCEPTUAL IMAGE PATCH SIMILARITY ( L P I P S )
# ==================================================================
# Author : Ashish Kumar Uchadiya
# Created : January 18, 2025
# Description: LPIPS essentially computes the similarity between the
# activations of two image patches for some pre-defined network.
# This measure has been shown to match human perception well.
# A low LPIPS score means that image patches are perceptual similar.
# ==================================================================
class vgg16(torch.nn.Module):
def __init__(self, requires_grad=False, pretrained=True):
super(vgg16, self).__init__()
vgg_pretrained_features = torchvision.models.vgg16(
weights=torchvision.models.VGG16_Weights.IMAGENET1K_V1
).features
self.slice1 = torch.nn.Sequential()
self.slice2 = torch.nn.Sequential()
self.slice3 = torch.nn.Sequential()
self.slice4 = torch.nn.Sequential()
self.slice5 = torch.nn.Sequential()
self.N_slices = 5
for x in range(4):
self.slice1.add_module(str(x), vgg_pretrained_features[x])
for x in range(4, 9):
self.slice2.add_module(str(x), vgg_pretrained_features[x])
for x in range(9, 16):
self.slice3.add_module(str(x), vgg_pretrained_features[x])
for x in range(16, 23):
self.slice4.add_module(str(x), vgg_pretrained_features[x])
for x in range(23, 30):
self.slice5.add_module(str(x), vgg_pretrained_features[x])
# Freeze vgg model
if not requires_grad:
for param in self.parameters():
param.requires_grad = False
def forward(self, X):
# Return output of vgg features
h = self.slice1(X)
h_relu1_2 = h
h = self.slice2(h)
h_relu2_2 = h
h = self.slice3(h)
h_relu3_3 = h
h = self.slice4(h)
h_relu4_3 = h
h = self.slice5(h)
h_relu5_3 = h
vgg_outputs = namedtuple("VggOutputs", ['relu1_2', 'relu2_2', 'relu3_3', 'relu4_3', 'relu5_3'])
out = vgg_outputs(h_relu1_2, h_relu2_2, h_relu3_3, h_relu4_3, h_relu5_3)
return out |