File size: 1,375 Bytes
4de73fc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import torch


def feature_loss(fmap_r, fmap_g):
    loss = 0
    for dr, dg in zip(fmap_r, fmap_g):
        for rl, gl in zip(dr, dg):
            rl = rl.float().detach()
            gl = gl.float()
            loss += torch.mean(torch.abs(rl - gl))

    return loss * 2


def discriminator_loss(disc_real_outputs, disc_generated_outputs):
    loss = 0
    r_losses = []
    g_losses = []
    for dr, dg in zip(disc_real_outputs, disc_generated_outputs):
        dr = dr.float()
        dg = dg.float()
        r_loss = torch.mean((1 - dr)**2)
        g_loss = torch.mean(dg**2)
        loss += (r_loss + g_loss)
        r_losses.append(r_loss.item())
        g_losses.append(g_loss.item())

    return loss, r_losses, g_losses


def generator_loss(disc_outputs):
    loss = 0
    gen_losses = []
    for dg in disc_outputs:
        dg = dg.float()
        l = torch.mean((1 - dg)**2)
        gen_losses.append(l)
        loss += l

    return loss, gen_losses


def kl_loss(z_p, logs_q, m_p, logs_p, z_mask):
    """
  z_p, logs_q: [b, h, t_t]
  m_p, logs_p: [b, h, t_t]
  """
    z_p = z_p.float()
    logs_q = logs_q.float()
    m_p = m_p.float()
    logs_p = logs_p.float()
    z_mask = z_mask.float()

    kl = logs_p - logs_q - 0.5
    kl += 0.5 * ((z_p - m_p)**2) * torch.exp(-2. * logs_p)
    kl = torch.sum(kl * z_mask)
    l = kl / torch.sum(z_mask)
    return l