96 lines
3.0 KiB
Python
96 lines
3.0 KiB
Python
import math
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
from timm.models.layers import trunc_normal_
|
|
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
|
|
|
|
|
def conv(in_planes, out_planes, kernel_size=3, stride=1, padding=1, dilation=1):
|
|
return nn.Sequential(
|
|
nn.Conv2d(
|
|
in_planes,
|
|
out_planes,
|
|
kernel_size=kernel_size,
|
|
stride=stride,
|
|
padding=padding,
|
|
dilation=dilation,
|
|
bias=True,
|
|
),
|
|
nn.PReLU(out_planes),
|
|
)
|
|
|
|
|
|
def deconv(in_planes, out_planes, kernel_size=4, stride=2, padding=1):
|
|
return nn.Sequential(
|
|
torch.nn.ConvTranspose2d(
|
|
in_channels=in_planes,
|
|
out_channels=out_planes,
|
|
kernel_size=4,
|
|
stride=2,
|
|
padding=1,
|
|
bias=True,
|
|
),
|
|
nn.PReLU(out_planes),
|
|
)
|
|
|
|
|
|
class Conv2(nn.Module):
|
|
def __init__(self, in_planes, out_planes, stride=2):
|
|
super(Conv2, self).__init__()
|
|
self.conv1 = conv(in_planes, out_planes, 3, stride, 1)
|
|
self.conv2 = conv(out_planes, out_planes, 3, 1, 1)
|
|
|
|
def forward(self, x):
|
|
x = self.conv1(x)
|
|
x = self.conv2(x)
|
|
return x
|
|
|
|
|
|
class Unet(nn.Module):
|
|
def __init__(self, c, M=False, out=3):
|
|
super(Unet, self).__init__()
|
|
self.down0 = Conv2(17 + c, 2 * c)
|
|
self.down1 = Conv2(4 * c, 4 * c)
|
|
self.down2 = Conv2(8 * c, 8 * c)
|
|
self.down3 = Conv2(16 * c, 16 * c)
|
|
self.up0 = deconv(32 * c if not M else 16 * c, 8 * c)
|
|
self.up1 = deconv(16 * c, 4 * c)
|
|
self.up2 = deconv(8 * c, 2 * c)
|
|
self.up3 = deconv(4 * c, c)
|
|
self.conv = nn.Conv2d(c, out, 3, 1, 1)
|
|
self.M = M
|
|
self.apply(self._init_weights)
|
|
|
|
def _init_weights(self, m):
|
|
if isinstance(m, nn.Linear):
|
|
trunc_normal_(m.weight, std=0.02)
|
|
if isinstance(m, nn.Linear) and m.bias is not None:
|
|
nn.init.constant_(m.bias, 0)
|
|
elif isinstance(m, nn.LayerNorm):
|
|
nn.init.constant_(m.bias, 0)
|
|
nn.init.constant_(m.weight, 1.0)
|
|
elif isinstance(m, nn.Conv2d):
|
|
fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
|
|
fan_out //= m.groups
|
|
m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
|
|
if m.bias is not None:
|
|
m.bias.data.zero_()
|
|
|
|
def forward(self, img0, img1, warped_img0, warped_img1, mask, flow, c0, c1):
|
|
s0 = self.down0(
|
|
torch.cat(
|
|
(img0, img1, warped_img0, warped_img1, mask, flow, c0[0], c1[0]), 1
|
|
)
|
|
)
|
|
s1 = self.down1(torch.cat((s0, c0[1], c1[1]), 1))
|
|
s2 = self.down2(torch.cat((s1, c0[2], c1[2]), 1))
|
|
s3 = self.down3(torch.cat((s2, c0[3], c1[3]), 1))
|
|
x = self.up0(torch.cat((s3, c0[4], c1[4]), 1) if not self.M else s3)
|
|
x = self.up1(torch.cat((x, s2), 1))
|
|
x = self.up2(torch.cat((x, s1), 1))
|
|
x = self.up3(torch.cat((x, s0), 1))
|
|
x = self.conv(x)
|
|
return torch.sigmoid(x)
|