| import torch |
| import torch.nn.functional as F |
| from torch.autograd import Variable |
| from math import exp |
| from lpips import LPIPS |
|
|
|
|
| def smooth_l1_loss(pred, target, beta=1.0): |
| diff = torch.abs(pred - target) |
| loss = torch.where(diff < beta, 0.5 * diff ** 2 / beta, diff - 0.5 * beta) |
| return loss.mean() |
|
|
|
|
| def l1_loss(network_output, gt): |
| return torch.abs((network_output - gt)).mean() |
|
|
|
|
| def l2_loss(network_output, gt): |
| return ((network_output - gt) ** 2).mean() |
|
|
|
|
| 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 psnr(img1, img2, max_val=1.0): |
| mse = F.mse_loss(img1, img2) |
| return 20 * torch.log10(max_val / torch.sqrt(mse)) |
|
|
|
|
| def ssim(img1, img2, window_size=11, size_average=True): |
| channel = img1.size(-3) |
| 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) |
|
|
| 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) |
|
|
|
|
| def load_lpips_ckpt(lpip_model, vgg_path): |
| vgg_ckpt = torch.load(vgg_path) |
| fea_ckpt = {k: v for k, v in vgg_ckpt.items() if 'features' in k} |
| lpip_ckpt = {} |
| for k, v in fea_ckpt.items(): |
| if '.0.' in k or '.2.' in k: |
| lpip_ckpt[k.replace('features', 'net.slice1')] = v |
| elif '.5.' in k or '.7.' in k: |
| lpip_ckpt[k.replace('features', 'net.slice2')] = v |
| elif '.10.' in k or '.12.' in k or '.14.' in k: |
| lpip_ckpt[k.replace('features', 'net.slice3')] = v |
| elif '.17.' in k or '.19.' in k or '.21.' in k: |
| lpip_ckpt[k.replace('features', 'net.slice4')] = v |
| elif '.24.' in k or '.26.' in k or '.28.' in k: |
| lpip_ckpt[k.replace('features', 'net.slice5')] = v |
| print(f'Load LPIPS Model: Number of matching keys: {len(set(lpip_model.state_dict().keys()).intersection(set(lpip_ckpt.keys())))}') |
| lpip_model.load_state_dict(lpip_ckpt, strict=False) |
| return lpip_model |
| |
|
|
| loss_fn_vgg = None |
| def lpips(img1, img2, value_range=(0, 1)): |
| global loss_fn_vgg |
| if loss_fn_vgg is None: |
| loss_fn_vgg = LPIPS(net='vgg', pnet_rand=True).cuda().eval() |
| load_lpips_ckpt(loss_fn_vgg, 'ckpts/vgg/vgg16-397923af.pth') |
| |
| img1 = (img1 - value_range[0]) / (value_range[1] - value_range[0]) * 2 - 1 |
| img2 = (img2 - value_range[0]) / (value_range[1] - value_range[0]) * 2 - 1 |
| return loss_fn_vgg(img1, img2).mean() |
|
|
|
|
| def normal_angle(pred, gt): |
| pred = pred * 2.0 - 1.0 |
| gt = gt * 2.0 - 1.0 |
| norms = pred.norm(dim=-1) * gt.norm(dim=-1) |
| cos_sim = (pred * gt).sum(-1) / (norms + 1e-9) |
| cos_sim = torch.clamp(cos_sim, -1.0, 1.0) |
| ang = torch.rad2deg(torch.acos(cos_sim[norms > 1e-9])).mean() |
| if ang.isnan(): |
| return -1 |
| return ang |
|
|
