File size: 2,738 Bytes
916b126
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
#
# Copyright (C) 2023, Inria
# GRAPHDECO research group, https://team.inria.fr/graphdeco
# All rights reserved.
#
# This software is free for non-commercial, research and evaluation use 
# under the terms of the LICENSE.md file.
#
# For inquiries contact  george.drettakis@inria.fr
#

import torch
import torch.nn.functional as F
from torch.autograd import Variable
from math import exp

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, sigma=1.5):
    _1D_window = gaussian(window_size, sigma).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_size=11, sigma=1.5, size_average=True, reduce=True):
    channel = img1.size(-3)
    window = create_window(window_size, channel, sigma)

    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, reduce)

def _ssim(img1, img2, window, window_size, channel, size_average=True, reduce=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 reduce:
        if size_average:
            return ssim_map.mean()
        else:
            return ssim_map.mean(1).mean(1).mean(1)
    else:
        return ssim_map

def _tensor_size(t):
    return t.size()[1]*t.size()[2]*t.size()[3]

def tv_loss(x):
    batch_size = x.size()[0]
    h_x = x.size()[2]
    w_x = x.size()[3]
    count_h = _tensor_size(x[:,:,1:,:])  
    count_w = _tensor_size(x[:,:,:,1:])
    h_tv = torch.pow((x[:,:,1:,:]-x[:,:,:h_x-1,:]),2).sum()  
    w_tv = torch.pow((x[:,:,:,1:]-x[:,:,:,:w_x-1]),2).sum()
    return 2*(h_tv/count_h+w_tv/count_w)/batch_size