mirror of
https://github.com/vladmandic/automatic
synced 2026-08-29 00:20:59 +02:00
CalamitousFelicitousness
dc4c58d0cb
- Vendor IFNet_HDv3 v4.25 (5 IFBlocks, Head encoder, feat channel) and v4 warplayer with explicit (tenFlow_div, backwarp_tenGrid) signature - Rewrite RifeModel.inference for the new forward signature with per-(H,W,device,dtype) caching of tenFlow_div and backwarp_tenGrid - Force fp32 inference: bf16 produced visible checkerboard at the new IFNet's depth (was hidden by v3.9's shallower architecture) - Crop padded frames in interpolate_nchw before output (was missing, produced gray bar on non-128-aligned inputs) - Drop training scaffolding (AdamW, EPE/SOBEL, update method) - Log obsolete legacy v3.9 weights file on first v4.25 load instead of silently deleting user data - Default download URL is HolyWu vs-rife mirror (MIT, byte-identical upstream weights); swap to project-hosted URL before merge
131 lines
4.5 KiB
Python
131 lines
4.5 KiB
Python
import torch
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F
|
|
|
|
from modules.rife.warplayer import warp
|
|
|
|
|
|
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.LeakyReLU(0.2, True),
|
|
)
|
|
|
|
|
|
class Head(nn.Module):
|
|
def __init__(self):
|
|
super(Head, self).__init__()
|
|
self.cnn0 = nn.Conv2d(3, 16, 3, 2, 1)
|
|
self.cnn1 = nn.Conv2d(16, 16, 3, 1, 1)
|
|
self.cnn2 = nn.Conv2d(16, 16, 3, 1, 1)
|
|
self.cnn3 = nn.ConvTranspose2d(16, 4, 4, 2, 1)
|
|
self.relu = nn.LeakyReLU(0.2, True)
|
|
|
|
def forward(self, x, feat=False):
|
|
x = x.clamp(0.0, 1.0)
|
|
x0 = self.cnn0(x)
|
|
x = self.relu(x0)
|
|
x1 = self.cnn1(x)
|
|
x = self.relu(x1)
|
|
x2 = self.cnn2(x)
|
|
x = self.relu(x2)
|
|
x3 = self.cnn3(x)
|
|
if feat:
|
|
return [x0, x1, x2, x3]
|
|
return x3
|
|
|
|
|
|
class ResConv(nn.Module):
|
|
def __init__(self, c, dilation=1):
|
|
super(ResConv, self).__init__()
|
|
self.conv = nn.Conv2d(c, c, 3, 1, dilation, dilation=dilation, groups=1)
|
|
self.beta = nn.Parameter(torch.ones((1, c, 1, 1)), requires_grad=True)
|
|
self.relu = nn.LeakyReLU(0.2, True)
|
|
|
|
def forward(self, x):
|
|
return self.relu(self.conv(x) * self.beta + x)
|
|
|
|
|
|
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.convblock = nn.Sequential(
|
|
ResConv(c),
|
|
ResConv(c),
|
|
ResConv(c),
|
|
ResConv(c),
|
|
ResConv(c),
|
|
ResConv(c),
|
|
ResConv(c),
|
|
ResConv(c),
|
|
)
|
|
self.lastconv = nn.Sequential(nn.ConvTranspose2d(c, 4 * 13, 4, 2, 1), nn.PixelShuffle(2))
|
|
|
|
def forward(self, x, flow=None, scale=1):
|
|
x = F.interpolate(x, scale_factor=1.0 / scale, mode="bilinear")
|
|
if flow is not None:
|
|
flow = F.interpolate(flow, scale_factor=1.0 / scale, mode="bilinear") / scale
|
|
x = torch.cat((x, flow), 1)
|
|
feat = self.conv0(x)
|
|
feat = self.convblock(feat)
|
|
tmp = self.lastconv(feat)
|
|
tmp = F.interpolate(tmp, scale_factor=scale, mode="bilinear")
|
|
flow = tmp[:, :4] * scale
|
|
mask = tmp[:, 4:5]
|
|
feat = tmp[:, 5:]
|
|
return flow, mask, feat
|
|
|
|
|
|
class IFNet(nn.Module):
|
|
def __init__(self, scale=1, ensemble=False):
|
|
super(IFNet, self).__init__()
|
|
self.block0 = IFBlock(7 + 8, c=192)
|
|
self.block1 = IFBlock(8 + 4 + 8 + 8, c=128)
|
|
self.block2 = IFBlock(8 + 4 + 8 + 8, c=96)
|
|
self.block3 = IFBlock(8 + 4 + 8 + 8, c=64)
|
|
self.block4 = IFBlock(8 + 4 + 8 + 8, c=32)
|
|
self.encode = Head()
|
|
self.scale_list = [16 / scale, 8 / scale, 4 / scale, 2 / scale, 1 / scale]
|
|
if ensemble:
|
|
raise ValueError("rife: ensemble is not supported in v4.25")
|
|
|
|
def forward(self, img0, img1, timestep, tenFlow_div, backwarp_tenGrid, f0, f1):
|
|
img0 = img0.clamp(0.0, 1.0)
|
|
img1 = img1.clamp(0.0, 1.0)
|
|
flow_list = []
|
|
merged = []
|
|
mask_list = []
|
|
warped_img0 = img0
|
|
warped_img1 = img1
|
|
flow = None
|
|
mask = None
|
|
block = [self.block0, self.block1, self.block2, self.block3, self.block4]
|
|
for i in range(5):
|
|
if flow is None:
|
|
flow, mask, feat = block[i](
|
|
torch.cat((img0, img1, f0, f1, timestep), 1), None, scale=self.scale_list[i]
|
|
)
|
|
else:
|
|
wf0 = warp(f0, flow[:, :2], tenFlow_div, backwarp_tenGrid)
|
|
wf1 = warp(f1, flow[:, 2:4], tenFlow_div, backwarp_tenGrid)
|
|
fd, m0, feat = block[i](
|
|
torch.cat((warped_img0, warped_img1, wf0, wf1, timestep, mask, feat), 1),
|
|
flow,
|
|
scale=self.scale_list[i],
|
|
)
|
|
mask = m0
|
|
flow = flow + fd
|
|
mask_list.append(mask)
|
|
flow_list.append(flow)
|
|
warped_img0 = warp(img0, flow[:, :2], tenFlow_div, backwarp_tenGrid)
|
|
warped_img1 = warp(img1, flow[:, 2:4], tenFlow_div, backwarp_tenGrid)
|
|
merged.append((warped_img0, warped_img1))
|
|
mask = torch.sigmoid(mask)
|
|
return warped_img0 * mask + warped_img1 * (1 - mask)
|