| import torch | |
| import torch.nn.functional as F | |
| from math import exp | |
| device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') | |
| 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=1): | |
| _1D_window = gaussian(window_size, 1.5).unsqueeze(1) | |
| _2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0).to(device) | |
| window = _2D_window.expand(channel, 1, window_size, window_size).contiguous() | |
| return window | |
| def create_window_3d(window_size, channel=1): | |
| _1D_window = gaussian(window_size, 1.5).unsqueeze(1) | |
| _2D_window = _1D_window.mm(_1D_window.t()) | |
| _3D_window = _2D_window.unsqueeze(2) @ (_1D_window.t()) | |
| window = _3D_window.expand(1, channel, window_size, window_size, window_size).contiguous().to(device) | |
| return window | |
| def ssim(img1, img2, window_size=11, window=None, size_average=True, full=False, val_range=None): | |
| if val_range is None: | |
| if torch.max(img1) > 128: | |
| max_val = 255 | |
| else: | |
| max_val = 1 | |
| if torch.min(img1) < -0.5: | |
| min_val = -1 | |
| else: | |
| min_val = 0 | |
| L = max_val - min_val | |
| else: | |
| L = val_range | |
| padd = 0 | |
| (_, channel, height, width) = img1.size() | |
| if window is None: | |
| real_size = min(window_size, height, width) | |
| window = create_window(real_size, channel=channel).to(img1.device) | |
| mu1 = F.conv2d(F.pad(img1, (5, 5, 5, 5), mode='replicate'), window, padding=padd, groups=channel) | |
| mu2 = F.conv2d(F.pad(img2, (5, 5, 5, 5), mode='replicate'), window, padding=padd, groups=channel) | |
| mu1_sq = mu1.pow(2) | |
| mu2_sq = mu2.pow(2) | |
| mu1_mu2 = mu1 * mu2 | |
| sigma1_sq = F.conv2d(F.pad(img1 * img1, (5, 5, 5, 5), 'replicate'), window, padding=padd, groups=channel) - mu1_sq | |
| sigma2_sq = F.conv2d(F.pad(img2 * img2, (5, 5, 5, 5), 'replicate'), window, padding=padd, groups=channel) - mu2_sq | |
| sigma12 = F.conv2d(F.pad(img1 * img2, (5, 5, 5, 5), 'replicate'), window, padding=padd, groups=channel) - mu1_mu2 | |
| C1 = (0.01 * L) ** 2 | |
| C2 = (0.03 * L) ** 2 | |
| v1 = 2.0 * sigma12 + C2 | |
| v2 = sigma1_sq + sigma2_sq + C2 | |
| cs = torch.mean(v1 / v2) | |
| ssim_map = ((2 * mu1_mu2 + C1) * v1) / ((mu1_sq + mu2_sq + C1) * v2) | |
| if size_average: | |
| ret = ssim_map.mean() | |
| else: | |
| ret = ssim_map.mean(1).mean(1).mean(1) | |
| if full: | |
| return ret, cs | |
| return ret | |
| def calculate_ssim(img1, img2, window_size=11, window=None, size_average=True, full=False, val_range=None): | |
| if val_range is None: | |
| if torch.max(img1) > 128: | |
| max_val = 255 | |
| else: | |
| max_val = 1 | |
| if torch.min(img1) < -0.5: | |
| min_val = -1 | |
| else: | |
| min_val = 0 | |
| L = max_val - min_val | |
| else: | |
| L = val_range | |
| padd = 0 | |
| (_, _, height, width) = img1.size() | |
| if window is None: | |
| real_size = min(window_size, height, width) | |
| window = create_window_3d(real_size, channel=1).to(img1.device) | |
| img1 = img1.unsqueeze(1) | |
| img2 = img2.unsqueeze(1) | |
| mu1 = F.conv3d(F.pad(img1, (5, 5, 5, 5, 5, 5), mode='replicate'), window, padding=padd, groups=1) | |
| mu2 = F.conv3d(F.pad(img2, (5, 5, 5, 5, 5, 5), mode='replicate'), window, padding=padd, groups=1) | |
| mu1_sq = mu1.pow(2) | |
| mu2_sq = mu2.pow(2) | |
| mu1_mu2 = mu1 * mu2 | |
| sigma1_sq = F.conv3d(F.pad(img1 * img1, (5, 5, 5, 5, 5, 5), 'replicate'), window, padding=padd, groups=1) - mu1_sq | |
| sigma2_sq = F.conv3d(F.pad(img2 * img2, (5, 5, 5, 5, 5, 5), 'replicate'), window, padding=padd, groups=1) - mu2_sq | |
| sigma12 = F.conv3d(F.pad(img1 * img2, (5, 5, 5, 5, 5, 5), 'replicate'), window, padding=padd, groups=1) - mu1_mu2 | |
| C1 = (0.01 * L) ** 2 | |
| C2 = (0.03 * L) ** 2 | |
| v1 = 2.0 * sigma12 + C2 | |
| v2 = sigma1_sq + sigma2_sq + C2 | |
| cs = torch.mean(v1 / v2) | |
| ssim_map = ((2 * mu1_mu2 + C1) * v1) / ((mu1_sq + mu2_sq + C1) * v2) | |
| if size_average: | |
| ret = ssim_map.mean() | |
| else: | |
| ret = ssim_map.mean(1).mean(1).mean(1) | |
| if full: | |
| return ret, cs | |
| return ret.detach().cpu().numpy() | |
| def calculate_psnr(img1, img2): | |
| psnr = -10 * torch.log10(((img1 - img2) * (img1 - img2)).mean()) | |
| return psnr.detach().cpu().numpy() | |
| def calculate_ie(img1, img2): | |
| ie = torch.abs(torch.round(img1 * 255.0) - torch.round(img2 * 255.0)).mean() | |
| return ie.detach().cpu().numpy() | |