import PIL, torch, torchvision
from torch.nn import functional as F
+
class MultiScaleEdgeEnergy(torch.nn.Module):
def __init__(self):
- super(MultiScaleEdgeEnergy, self).__init__()
- k = torch.exp(- torch.tensor([[-2., -1., 0., 1., 2.]])**2 / 2)
+ super().__init__()
+ k = torch.exp(-torch.tensor([[-2.0, -1.0, 0.0, 1.0, 2.0]]) ** 2 / 2)
k = (k.t() @ k).view(1, 1, 5, 5)
self.gaussian_5x5 = torch.nn.Parameter(k / k.sum()).requires_grad_(False)
u = x.view(-1, 1, x.size(2), x.size(3))
result = 0.0
while min(u.size(2), u.size(3)) > 5:
- blurry = F.conv2d(u, self.gaussian_5x5, padding = 2)
+ blurry = F.conv2d(u, self.gaussian_5x5, padding=2)
result += (u - blurry).view(u.size(0), -1).pow(2).sum(1)
- u = F.avg_pool2d(u, kernel_size = 2, padding = 1)
+ u = F.avg_pool2d(u, kernel_size=2, padding=1)
return result.view(x.size(0), -1).sum(1)
-img = torchvision.transforms.ToTensor()(PIL.Image.open('blacklab.jpg'))
+
+img = torchvision.transforms.ToTensor()(PIL.Image.open("blacklab.jpg"))
img = img.view((1,) + img.size())
ref_input = 0.5 + 0.5 * (img - img.mean()) / img.std()
mse_loss = torch.nn.MSELoss()
edge_energy = MultiScaleEdgeEnergy()
-layers = torchvision.models.vgg16(pretrained = True).features
+layers = torchvision.models.vgg16(pretrained=True).features
layers.eval()
if torch.cuda.is_available():
ref_input = ref_input.cuda()
layers.cuda()
-for l in [ 5, 7, 12, 17, 21, 28 ]:
+for l in [5, 7, 12, 17, 21, 28]:
model = torch.nn.Sequential(layers[:l])
ref_output = model(ref_input).detach()
for n in range(5):
input = torch.empty_like(ref_input).uniform_(-0.01, 0.01).requires_grad_()
- optimizer = torch.optim.Adam( [ input ], lr = 1e-2)
+ optimizer = torch.optim.Adam([input], lr=1e-2)
for k in range(1000):
output = model(input)
loss = mse_loss(output, ref_output) + 1e-3 * edge_energy(input)
optimizer.step()
img = 0.5 + 0.2 * (input - input.mean()) / input.std()
- result_name = 'hallu-l%02d-n%02d.png' % (l, n)
+ result_name = "hallu-l%02d-n%02d.png" % (l, n)
torchvision.utils.save_image(img, result_name)
- print('Wrote ' + result_name)
+ print("Wrote " + result_name)