LDM/scripts/_1_Lpips.py

# ==================================================================
#        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