Spaces:
Paused
Paused
File size: 5,148 Bytes
8502051 |
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 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 |
import torch
import torch.nn as nn
import torch.nn.functional as F
from diffusers import ModelMixin
from .warplayer import warp
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 conv_bn(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=False),
nn.BatchNorm2d(out_planes),
nn.PReLU(out_planes)
)
def convert(param):
return {
k.replace("module.", ""): v
for k, v in param.items()
if "module." in k
}
class IFBlock(nn.Module):
def __init__(self, in_planes, c=64):
super(IFBlock, self).__init__()
self.conv0 = nn.Sequential(
conv(in_planes, c//2, 3, 2, 1),
conv(c//2, c, 3, 2, 1),
)
self.convblock0 = nn.Sequential(
conv(c, c),
conv(c, c)
)
self.convblock1 = nn.Sequential(
conv(c, c),
conv(c, c)
)
self.convblock2 = nn.Sequential(
conv(c, c),
conv(c, c)
)
self.convblock3 = nn.Sequential(
conv(c, c),
conv(c, c)
)
self.conv1 = nn.Sequential(
nn.ConvTranspose2d(c, c//2, 4, 2, 1),
nn.PReLU(c//2),
nn.ConvTranspose2d(c//2, 4, 4, 2, 1),
)
self.conv2 = nn.Sequential(
nn.ConvTranspose2d(c, c//2, 4, 2, 1),
nn.PReLU(c//2),
nn.ConvTranspose2d(c//2, 1, 4, 2, 1),
)
def forward(self, x, flow, scale=1):
x = F.interpolate(x, scale_factor= 1. / scale, mode="bilinear", align_corners=False, recompute_scale_factor=False)
flow = F.interpolate(flow, scale_factor= 1. / scale, mode="bilinear", align_corners=False, recompute_scale_factor=False) * 1. / scale
feat = self.conv0(torch.cat((x, flow), 1))
feat = self.convblock0(feat) + feat
feat = self.convblock1(feat) + feat
feat = self.convblock2(feat) + feat
feat = self.convblock3(feat) + feat
flow = self.conv1(feat)
mask = self.conv2(feat)
flow = F.interpolate(flow, scale_factor=scale, mode="bilinear", align_corners=False, recompute_scale_factor=False) * scale
mask = F.interpolate(mask, scale_factor=scale, mode="bilinear", align_corners=False, recompute_scale_factor=False)
return flow, mask
class IFNet(ModelMixin):
def __init__(self, ckpt_path="checkpoints/flownet.pkl"):
super(IFNet, self).__init__()
self.block0 = IFBlock(7+4, c=90)
self.block1 = IFBlock(7+4, c=90)
self.block2 = IFBlock(7+4, c=90)
self.block_tea = IFBlock(10+4, c=90)
if ckpt_path is not None:
self.load_state_dict(convert(torch.load(ckpt_path, map_location ='cpu')))
def inference(self, img0, img1, scale=1.0):
imgs = torch.cat((img0, img1), 1)
scale_list = [4/scale, 2/scale, 1/scale]
flow, mask, merged = self.forward(imgs, scale_list)
return merged[2]
def forward(self, x, scale_list=[4, 2, 1], training=False):
if training == False:
channel = x.shape[1] // 2
img0 = x[:, :channel]
img1 = x[:, channel:]
flow_list = []
merged = []
mask_list = []
warped_img0 = img0
warped_img1 = img1
flow = (x[:, :4]).detach() * 0
mask = (x[:, :1]).detach() * 0
loss_cons = 0
block = [self.block0, self.block1, self.block2]
for i in range(3):
f0, m0 = block[i](torch.cat((warped_img0[:, :3], warped_img1[:, :3], mask), 1), flow, scale=scale_list[i])
f1, m1 = block[i](torch.cat((warped_img1[:, :3], warped_img0[:, :3], -mask), 1), torch.cat((flow[:, 2:4], flow[:, :2]), 1), scale=scale_list[i])
flow = flow + (f0 + torch.cat((f1[:, 2:4], f1[:, :2]), 1)) / 2
mask = mask + (m0 + (-m1)) / 2
mask_list.append(mask)
flow_list.append(flow)
warped_img0 = warp(img0, flow[:, :2])
warped_img1 = warp(img1, flow[:, 2:4])
merged.append((warped_img0, warped_img1))
'''
c0 = self.contextnet(img0, flow[:, :2])
c1 = self.contextnet(img1, flow[:, 2:4])
tmp = self.unet(img0, img1, warped_img0, warped_img1, mask, flow, c0, c1)
res = tmp[:, 1:4] * 2 - 1
'''
for i in range(3):
mask_list[i] = torch.sigmoid(mask_list[i])
merged[i] = merged[i][0] * mask_list[i] + merged[i][1] * (1 - mask_list[i])
# merged[i] = torch.clamp(merged[i] + res, 0, 1)
return flow_list, mask_list[2], merged
|