Spaces:
Running
Running
File size: 3,708 Bytes
2514fb4 |
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 |
import torch
import torch.nn.functional as F
from torch.autograd import Variable
import numpy as np
from math import exp
"""
# ============================================
# SSIM loss
# https://github.com/Po-Hsun-Su/pytorch-ssim
# ============================================
"""
def gaussian(window_size, sigma):
gauss = torch.Tensor([exp(-(x - window_size//2)**2/float(2*sigma**2)) for x in range(window_size)])
return gauss/gauss.sum()
def create_window(window_size, channel):
_1D_window = gaussian(window_size, 1.5).unsqueeze(1)
_2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0)
window = Variable(_2D_window.expand(channel, 1, window_size, window_size).contiguous())
return window
def _ssim(img1, img2, window, window_size, channel, size_average=True):
mu1 = F.conv2d(img1, window, padding=window_size//2, groups=channel)
mu2 = F.conv2d(img2, window, padding=window_size//2, groups=channel)
mu1_sq = mu1.pow(2)
mu2_sq = mu2.pow(2)
mu1_mu2 = mu1*mu2
sigma1_sq = F.conv2d(img1*img1, window, padding=window_size//2, groups=channel) - mu1_sq
sigma2_sq = F.conv2d(img2*img2, window, padding=window_size//2, groups=channel) - mu2_sq
sigma12 = F.conv2d(img1*img2, window, padding=window_size//2, groups=channel) - mu1_mu2
C1 = 0.01**2
C2 = 0.03**2
ssim_map = ((2*mu1_mu2 + C1)*(2*sigma12 + C2))/((mu1_sq + mu2_sq + C1)*(sigma1_sq + sigma2_sq + C2))
if size_average:
return ssim_map.mean()
else:
return ssim_map.mean(1).mean(1).mean(1)
class SSIMLoss(torch.nn.Module):
def __init__(self, window_size=11, size_average=True):
super(SSIMLoss, self).__init__()
self.window_size = window_size
self.size_average = size_average
self.channel = 1
self.window = create_window(window_size, self.channel)
def forward(self, img1, img2):
(_, channel, _, _) = img1.size()
if channel == self.channel and self.window.data.type() == img1.data.type():
window = self.window
else:
window = create_window(self.window_size, channel)
if img1.is_cuda:
window = window.cuda(img1.get_device())
window = window.type_as(img1)
self.window = window
self.channel = channel
return _ssim(img1, img2, window, self.window_size, channel, self.size_average)
def ssim(img1, img2, window_size=11, size_average=True):
(_, channel, _, _) = img1.size()
window = create_window(window_size, channel)
if img1.is_cuda:
window = window.cuda(img1.get_device())
window = window.type_as(img1)
return _ssim(img1, img2, window, window_size, channel, size_average)
if __name__ == '__main__':
import cv2
from torch import optim
from skimage import io
npImg1 = cv2.imread("einstein.png")
img1 = torch.from_numpy(np.rollaxis(npImg1, 2)).float().unsqueeze(0)/255.0
img2 = torch.rand(img1.size())
if torch.cuda.is_available():
img1 = img1.cuda()
img2 = img2.cuda()
img1 = Variable(img1, requires_grad=False)
img2 = Variable(img2, requires_grad=True)
ssim_value = ssim(img1, img2).item()
print("Initial ssim:", ssim_value)
ssim_loss = SSIMLoss()
optimizer = optim.Adam([img2], lr=0.01)
while ssim_value < 0.99:
optimizer.zero_grad()
ssim_out = -ssim_loss(img1, img2)
ssim_value = -ssim_out.item()
print('{:<4.4f}'.format(ssim_value))
ssim_out.backward()
optimizer.step()
img = np.transpose(img2.detach().cpu().squeeze().float().numpy(), (1,2,0))
io.imshow(np.uint8(np.clip(img*255, 0, 255)))
|