|
|
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) |
|
|
|
|
|
|
|
|
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').cuda().eval() |
|
|
|
|
|
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 |
|
|
|
