mirror of
https://github.com/n00mkrad/flowframes.git
synced 2025-12-16 08:27:44 +01:00
Updated RIFE-CUDA code (synced with local code)
This commit is contained in:
N00MKRAD
@@ -1,81 +0,0 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
from model_v3_legacy.warplayer import warp
|
||||
|
||||
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),
|
||||
nn.PReLU(out_planes)
|
||||
)
|
||||
|
||||
def conv_wo_act(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),
|
||||
)
|
||||
|
||||
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)
|
||||
)
|
||||
|
||||
class IFBlock(nn.Module):
|
||||
def __init__(self, in_planes, c=64):
|
||||
super(IFBlock, self).__init__()
|
||||
self.conv0 = nn.Sequential(
|
||||
conv(in_planes, c, 3, 2, 1),
|
||||
conv(c, 2*c, 3, 2, 1),
|
||||
)
|
||||
self.convblock0 = nn.Sequential(
|
||||
conv(2*c, 2*c),
|
||||
conv(2*c, 2*c),
|
||||
)
|
||||
self.convblock1 = nn.Sequential(
|
||||
conv(2*c, 2*c),
|
||||
conv(2*c, 2*c),
|
||||
)
|
||||
self.convblock2 = nn.Sequential(
|
||||
conv(2*c, 2*c),
|
||||
conv(2*c, 2*c),
|
||||
)
|
||||
self.conv1 = nn.ConvTranspose2d(2*c, 4, 4, 2, 1)
|
||||
|
||||
def forward(self, x, flow=None, scale=1):
|
||||
x = F.interpolate(x, scale_factor= 1. / scale, mode="bilinear", align_corners=False)
|
||||
if flow != None:
|
||||
flow = F.interpolate(flow, scale_factor= 1. / scale, mode="bilinear", align_corners=False) * (1. / scale)
|
||||
x = torch.cat((x, flow), 1)
|
||||
x = self.conv0(x)
|
||||
x = self.convblock0(x) + x
|
||||
x = self.convblock1(x) + x
|
||||
x = self.convblock2(x) + x
|
||||
x = self.conv1(x)
|
||||
flow = x
|
||||
if scale != 1:
|
||||
flow = F.interpolate(flow, scale_factor= scale, mode="bilinear", align_corners=False) * scale
|
||||
return flow
|
||||
|
||||
class IFNet(nn.Module):
|
||||
def __init__(self):
|
||||
super(IFNet, self).__init__()
|
||||
self.block0 = IFBlock(6, c=80)
|
||||
self.block1 = IFBlock(10, c=80)
|
||||
self.block2 = IFBlock(10, c=80)
|
||||
|
||||
def forward(self, x, scale_list=[4,2,1]):
|
||||
flow0 = self.block0(x, scale=scale_list[0])
|
||||
F1 = flow0
|
||||
F1_large = F.interpolate(F1, scale_factor=2.0, mode="bilinear", align_corners=False) * 2.0
|
||||
warped_img0 = warp(x[:, :3], F1_large[:, :2])
|
||||
warped_img1 = warp(x[:, 3:], F1_large[:, 2:4])
|
||||
flow1 = self.block1(torch.cat((warped_img0, warped_img1), 1), F1_large, scale=scale_list[1])
|
||||
F2 = (flow0 + flow1)
|
||||
F2_large = F.interpolate(F2, scale_factor=2.0, mode="bilinear", align_corners=False) * 2.0
|
||||
warped_img0 = warp(x[:, :3], F2_large[:, :2])
|
||||
warped_img1 = warp(x[:, 3:], F2_large[:, 2:4])
|
||||
flow2 = self.block2(torch.cat((warped_img0, warped_img1), 1), F2_large, scale=scale_list[2])
|
||||
F3 = (flow0 + flow1 + flow2)
|
||||
return F3, [F1, F2, F3]
|
||||
@@ -1,249 +0,0 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import numpy as np
|
||||
from torch.optim import AdamW
|
||||
import torch.optim as optim
|
||||
import itertools
|
||||
from model_v3_legacy.warplayer import warp
|
||||
from torch.nn.parallel import DistributedDataParallel as DDP
|
||||
from model_v3_legacy.IFNet_HDv3 import *
|
||||
import torch.nn.functional as F
|
||||
from model_v3_legacy.loss import *
|
||||
|
||||
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)
|
||||
)
|
||||
|
||||
def conv_woact(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),
|
||||
)
|
||||
|
||||
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
|
||||
|
||||
c = 32
|
||||
|
||||
class ContextNet(nn.Module):
|
||||
def __init__(self):
|
||||
super(ContextNet, self).__init__()
|
||||
self.conv0 = Conv2(3, c)
|
||||
self.conv1 = Conv2(c, c)
|
||||
self.conv2 = Conv2(c, 2*c)
|
||||
self.conv3 = Conv2(2*c, 4*c)
|
||||
self.conv4 = Conv2(4*c, 8*c)
|
||||
|
||||
def forward(self, x, flow):
|
||||
x = self.conv0(x)
|
||||
x = self.conv1(x)
|
||||
flow = F.interpolate(flow, scale_factor=0.5, mode="bilinear", align_corners=False) * 0.5
|
||||
f1 = warp(x, flow)
|
||||
x = self.conv2(x)
|
||||
flow = F.interpolate(flow, scale_factor=0.5, mode="bilinear",
|
||||
align_corners=False) * 0.5
|
||||
f2 = warp(x, flow)
|
||||
x = self.conv3(x)
|
||||
flow = F.interpolate(flow, scale_factor=0.5, mode="bilinear",
|
||||
align_corners=False) * 0.5
|
||||
f3 = warp(x, flow)
|
||||
x = self.conv4(x)
|
||||
flow = F.interpolate(flow, scale_factor=0.5, mode="bilinear",
|
||||
align_corners=False) * 0.5
|
||||
f4 = warp(x, flow)
|
||||
return [f1, f2, f3, f4]
|
||||
|
||||
|
||||
class FusionNet(nn.Module):
|
||||
def __init__(self):
|
||||
super(FusionNet, self).__init__()
|
||||
self.conv0 = Conv2(10, c)
|
||||
self.down0 = Conv2(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, 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.ConvTranspose2d(c, 4, 4, 2, 1)
|
||||
|
||||
def forward(self, img0, img1, flow, c0, c1, flow_gt):
|
||||
warped_img0 = warp(img0, flow[:, :2])
|
||||
warped_img1 = warp(img1, flow[:, 2:4])
|
||||
if flow_gt == None:
|
||||
warped_img0_gt, warped_img1_gt = None, None
|
||||
else:
|
||||
warped_img0_gt = warp(img0, flow_gt[:, :2])
|
||||
warped_img1_gt = warp(img1, flow_gt[:, 2:4])
|
||||
x = self.conv0(torch.cat((warped_img0, warped_img1, flow), 1))
|
||||
s0 = self.down0(x)
|
||||
s1 = self.down1(torch.cat((s0, c0[0], c1[0]), 1))
|
||||
s2 = self.down2(torch.cat((s1, c0[1], c1[1]), 1))
|
||||
s3 = self.down3(torch.cat((s2, c0[2], c1[2]), 1))
|
||||
x = self.up0(torch.cat((s3, c0[3], c1[3]), 1))
|
||||
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 x, warped_img0, warped_img1, warped_img0_gt, warped_img1_gt
|
||||
|
||||
|
||||
class Model:
|
||||
def __init__(self, local_rank=-1):
|
||||
self.flownet = IFNet()
|
||||
self.contextnet = ContextNet()
|
||||
self.fusionnet = FusionNet()
|
||||
self.device()
|
||||
self.optimG = AdamW(itertools.chain(
|
||||
self.flownet.parameters(),
|
||||
self.contextnet.parameters(),
|
||||
self.fusionnet.parameters()), lr=1e-6, weight_decay=1e-5)
|
||||
self.schedulerG = optim.lr_scheduler.CyclicLR(
|
||||
self.optimG, base_lr=1e-6, max_lr=1e-3, step_size_up=8000, cycle_momentum=False)
|
||||
self.epe = EPE()
|
||||
self.ter = Ternary()
|
||||
self.sobel = SOBEL()
|
||||
if local_rank != -1:
|
||||
self.flownet = DDP(self.flownet, device_ids=[
|
||||
local_rank], output_device=local_rank)
|
||||
self.contextnet = DDP(self.contextnet, device_ids=[
|
||||
local_rank], output_device=local_rank)
|
||||
self.fusionnet = DDP(self.fusionnet, device_ids=[
|
||||
local_rank], output_device=local_rank)
|
||||
|
||||
def train(self):
|
||||
self.flownet.train()
|
||||
self.contextnet.train()
|
||||
self.fusionnet.train()
|
||||
|
||||
def eval(self):
|
||||
self.flownet.eval()
|
||||
self.contextnet.eval()
|
||||
self.fusionnet.eval()
|
||||
|
||||
def device(self):
|
||||
self.flownet.to(device)
|
||||
self.contextnet.to(device)
|
||||
self.fusionnet.to(device)
|
||||
|
||||
def load_model(self, path, rank):
|
||||
def convert(param):
|
||||
if rank == -1:
|
||||
return {
|
||||
k.replace("module.", ""): v
|
||||
for k, v in param.items()
|
||||
if "module." in k
|
||||
}
|
||||
else:
|
||||
return param
|
||||
if rank <= 0:
|
||||
self.flownet.load_state_dict(
|
||||
convert(torch.load('{}/flownet.pkl'.format(path), map_location=device)))
|
||||
self.contextnet.load_state_dict(
|
||||
convert(torch.load('{}/contextnet.pkl'.format(path), map_location=device)))
|
||||
self.fusionnet.load_state_dict(
|
||||
convert(torch.load('{}/unet.pkl'.format(path), map_location=device)))
|
||||
|
||||
def save_model(self, path, rank):
|
||||
if rank == 0:
|
||||
torch.save(self.flownet.state_dict(), '{}/flownet.pkl'.format(path))
|
||||
torch.save(self.contextnet.state_dict(), '{}/contextnet.pkl'.format(path))
|
||||
torch.save(self.fusionnet.state_dict(), '{}/unet.pkl'.format(path))
|
||||
|
||||
def predict(self, imgs, flow, training=True, flow_gt=None, UHD=False):
|
||||
img0 = imgs[:, :3]
|
||||
img1 = imgs[:, 3:]
|
||||
if UHD:
|
||||
flow = F.interpolate(flow, scale_factor=2.0, mode="bilinear", align_corners=False) * 2.0
|
||||
c0 = self.contextnet(img0, flow[:, :2])
|
||||
c1 = self.contextnet(img1, flow[:, 2:4])
|
||||
flow = F.interpolate(flow, scale_factor=2.0, mode="bilinear",
|
||||
align_corners=False) * 2.0
|
||||
refine_output, warped_img0, warped_img1, warped_img0_gt, warped_img1_gt = self.fusionnet(
|
||||
img0, img1, flow, c0, c1, flow_gt)
|
||||
res = torch.sigmoid(refine_output[:, :3]) * 2 - 1
|
||||
mask = torch.sigmoid(refine_output[:, 3:4])
|
||||
merged_img = warped_img0 * mask + warped_img1 * (1 - mask)
|
||||
pred = merged_img + res
|
||||
pred = torch.clamp(pred, 0, 1)
|
||||
if training:
|
||||
return pred, mask, merged_img, warped_img0, warped_img1, warped_img0_gt, warped_img1_gt
|
||||
else:
|
||||
return pred
|
||||
|
||||
def inference(self, img0, img1, UHD=False):
|
||||
imgs = torch.cat((img0, img1), 1)
|
||||
scale_list = [8, 4, 2]
|
||||
flow, _ = self.flownet(imgs, scale_list)
|
||||
res = self.predict(imgs, flow, training=False, UHD=False)
|
||||
return res
|
||||
|
||||
def update(self, imgs, gt, learning_rate=0, mul=1, training=True, flow_gt=None):
|
||||
for param_group in self.optimG.param_groups:
|
||||
param_group['lr'] = learning_rate
|
||||
if training:
|
||||
self.train()
|
||||
else:
|
||||
self.eval()
|
||||
flow, flow_list = self.flownet(imgs)
|
||||
pred, mask, merged_img, warped_img0, warped_img1, warped_img0_gt, warped_img1_gt = self.predict(
|
||||
imgs, flow, flow_gt=flow_gt)
|
||||
loss_ter = self.ter(pred, gt).mean()
|
||||
if training:
|
||||
with torch.no_grad():
|
||||
loss_flow = torch.abs(warped_img0_gt - gt).mean()
|
||||
loss_mask = torch.abs(
|
||||
merged_img - gt).sum(1, True).float().detach()
|
||||
loss_mask = F.interpolate(loss_mask, scale_factor=0.5, mode="bilinear",
|
||||
align_corners=False).detach()
|
||||
flow_gt = (F.interpolate(flow_gt, scale_factor=0.5, mode="bilinear",
|
||||
align_corners=False) * 0.5).detach()
|
||||
loss_cons = 0
|
||||
for i in range(4):
|
||||
loss_cons += self.epe(flow_list[i][:, :2], flow_gt[:, :2], 1)
|
||||
loss_cons += self.epe(flow_list[i][:, 2:4], flow_gt[:, 2:4], 1)
|
||||
loss_cons = loss_cons.mean() * 0.01
|
||||
else:
|
||||
loss_cons = torch.tensor([0])
|
||||
loss_flow = torch.abs(warped_img0 - gt).mean()
|
||||
loss_mask = 1
|
||||
loss_l1 = (((pred - gt) ** 2 + 1e-6) ** 0.5).mean()
|
||||
if training:
|
||||
self.optimG.zero_grad()
|
||||
loss_G = loss_l1 + loss_cons + loss_ter
|
||||
loss_G.backward()
|
||||
self.optimG.step()
|
||||
return pred, merged_img, flow, loss_l1, loss_flow, loss_cons, loss_ter, loss_mask
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
img0 = torch.zeros(3, 3, 256, 256).float().to(device)
|
||||
img1 = torch.tensor(np.random.normal(
|
||||
0, 1, (3, 3, 256, 256))).float().to(device)
|
||||
imgs = torch.cat((img0, img1), 1)
|
||||
model = Model()
|
||||
model.eval()
|
||||
print(model.inference(imgs).shape)
|
||||
@@ -1,128 +0,0 @@
|
||||
import torch
|
||||
import numpy as np
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import torchvision.models as models
|
||||
|
||||
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||
|
||||
|
||||
class EPE(nn.Module):
|
||||
def __init__(self):
|
||||
super(EPE, self).__init__()
|
||||
|
||||
def forward(self, flow, gt, loss_mask):
|
||||
loss_map = (flow - gt.detach()) ** 2
|
||||
loss_map = (loss_map.sum(1, True) + 1e-6) ** 0.5
|
||||
return (loss_map * loss_mask)
|
||||
|
||||
|
||||
class Ternary(nn.Module):
|
||||
def __init__(self):
|
||||
super(Ternary, self).__init__()
|
||||
patch_size = 7
|
||||
out_channels = patch_size * patch_size
|
||||
self.w = np.eye(out_channels).reshape(
|
||||
(patch_size, patch_size, 1, out_channels))
|
||||
self.w = np.transpose(self.w, (3, 2, 0, 1))
|
||||
self.w = torch.tensor(self.w).float().to(device)
|
||||
|
||||
def transform(self, img):
|
||||
patches = F.conv2d(img, self.w, padding=3, bias=None)
|
||||
transf = patches - img
|
||||
transf_norm = transf / torch.sqrt(0.81 + transf**2)
|
||||
return transf_norm
|
||||
|
||||
def rgb2gray(self, rgb):
|
||||
r, g, b = rgb[:, 0:1, :, :], rgb[:, 1:2, :, :], rgb[:, 2:3, :, :]
|
||||
gray = 0.2989 * r + 0.5870 * g + 0.1140 * b
|
||||
return gray
|
||||
|
||||
def hamming(self, t1, t2):
|
||||
dist = (t1 - t2) ** 2
|
||||
dist_norm = torch.mean(dist / (0.1 + dist), 1, True)
|
||||
return dist_norm
|
||||
|
||||
def valid_mask(self, t, padding):
|
||||
n, _, h, w = t.size()
|
||||
inner = torch.ones(n, 1, h - 2 * padding, w - 2 * padding).type_as(t)
|
||||
mask = F.pad(inner, [padding] * 4)
|
||||
return mask
|
||||
|
||||
def forward(self, img0, img1):
|
||||
img0 = self.transform(self.rgb2gray(img0))
|
||||
img1 = self.transform(self.rgb2gray(img1))
|
||||
return self.hamming(img0, img1) * self.valid_mask(img0, 1)
|
||||
|
||||
|
||||
class SOBEL(nn.Module):
|
||||
def __init__(self):
|
||||
super(SOBEL, self).__init__()
|
||||
self.kernelX = torch.tensor([
|
||||
[1, 0, -1],
|
||||
[2, 0, -2],
|
||||
[1, 0, -1],
|
||||
]).float()
|
||||
self.kernelY = self.kernelX.clone().T
|
||||
self.kernelX = self.kernelX.unsqueeze(0).unsqueeze(0).to(device)
|
||||
self.kernelY = self.kernelY.unsqueeze(0).unsqueeze(0).to(device)
|
||||
|
||||
def forward(self, pred, gt):
|
||||
N, C, H, W = pred.shape[0], pred.shape[1], pred.shape[2], pred.shape[3]
|
||||
img_stack = torch.cat(
|
||||
[pred.reshape(N*C, 1, H, W), gt.reshape(N*C, 1, H, W)], 0)
|
||||
sobel_stack_x = F.conv2d(img_stack, self.kernelX, padding=1)
|
||||
sobel_stack_y = F.conv2d(img_stack, self.kernelY, padding=1)
|
||||
pred_X, gt_X = sobel_stack_x[:N*C], sobel_stack_x[N*C:]
|
||||
pred_Y, gt_Y = sobel_stack_y[:N*C], sobel_stack_y[N*C:]
|
||||
|
||||
L1X, L1Y = torch.abs(pred_X-gt_X), torch.abs(pred_Y-gt_Y)
|
||||
loss = (L1X+L1Y)
|
||||
return loss
|
||||
|
||||
class MeanShift(nn.Conv2d):
|
||||
def __init__(self, data_mean, data_std, data_range=1, norm=True):
|
||||
c = len(data_mean)
|
||||
super(MeanShift, self).__init__(c, c, kernel_size=1)
|
||||
std = torch.Tensor(data_std)
|
||||
self.weight.data = torch.eye(c).view(c, c, 1, 1)
|
||||
if norm:
|
||||
self.weight.data.div_(std.view(c, 1, 1, 1))
|
||||
self.bias.data = -1 * data_range * torch.Tensor(data_mean)
|
||||
self.bias.data.div_(std)
|
||||
else:
|
||||
self.weight.data.mul_(std.view(c, 1, 1, 1))
|
||||
self.bias.data = data_range * torch.Tensor(data_mean)
|
||||
self.requires_grad = False
|
||||
|
||||
class VGGPerceptualLoss(torch.nn.Module):
|
||||
def __init__(self, rank=0):
|
||||
super(VGGPerceptualLoss, self).__init__()
|
||||
blocks = []
|
||||
pretrained = True
|
||||
self.vgg_pretrained_features = models.vgg19(pretrained=pretrained).features
|
||||
self.normalize = MeanShift([0.485, 0.456, 0.406], [0.229, 0.224, 0.225], norm=True).cuda()
|
||||
for param in self.parameters():
|
||||
param.requires_grad = False
|
||||
|
||||
def forward(self, X, Y, indices=None):
|
||||
X = self.normalize(X)
|
||||
Y = self.normalize(Y)
|
||||
indices = [2, 7, 12, 21, 30]
|
||||
weights = [1.0/2.6, 1.0/4.8, 1.0/3.7, 1.0/5.6, 10/1.5]
|
||||
k = 0
|
||||
loss = 0
|
||||
for i in range(indices[-1]):
|
||||
X = self.vgg_pretrained_features[i](X)
|
||||
Y = self.vgg_pretrained_features[i](Y)
|
||||
if (i+1) in indices:
|
||||
loss += weights[k] * (X - Y.detach()).abs().mean() * 0.1
|
||||
k += 1
|
||||
return loss
|
||||
|
||||
if __name__ == '__main__':
|
||||
img0 = torch.zeros(3, 3, 256, 256).float().to(device)
|
||||
img1 = torch.tensor(np.random.normal(
|
||||
0, 1, (3, 3, 256, 256))).float().to(device)
|
||||
ternary_loss = Ternary()
|
||||
print(ternary_loss(img0, img1).shape)
|
||||
@@ -1,22 +0,0 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||
backwarp_tenGrid = {}
|
||||
|
||||
|
||||
def warp(tenInput, tenFlow):
|
||||
k = (str(tenFlow.device), str(tenFlow.size()))
|
||||
if k not in backwarp_tenGrid:
|
||||
tenHorizontal = torch.linspace(-1.0, 1.0, tenFlow.shape[3], device=device).view(
|
||||
1, 1, 1, tenFlow.shape[3]).expand(tenFlow.shape[0], -1, tenFlow.shape[2], -1)
|
||||
tenVertical = torch.linspace(-1.0, 1.0, tenFlow.shape[2], device=device).view(
|
||||
1, 1, tenFlow.shape[2], 1).expand(tenFlow.shape[0], -1, -1, tenFlow.shape[3])
|
||||
backwarp_tenGrid[k] = torch.cat(
|
||||
[tenHorizontal, tenVertical], 1).to(device)
|
||||
|
||||
tenFlow = torch.cat([tenFlow[:, 0:1, :, :] / ((tenInput.shape[3] - 1.0) / 2.0),
|
||||
tenFlow[:, 1:2, :, :] / ((tenInput.shape[2] - 1.0) / 2.0)], 1)
|
||||
|
||||
g = (backwarp_tenGrid[k] + tenFlow).permute(0, 2, 3, 1)
|
||||
return torch.nn.functional.grid_sample(input=tenInput, grid=g, mode='bilinear', padding_mode='border', align_corners=True)
|
||||
@@ -26,15 +26,15 @@
|
||||
{
|
||||
"name": "RIFE 3.1",
|
||||
"desc": "Updated v3 General Model",
|
||||
"supportsAlpha": "false",
|
||||
"dir": "RIFE31",
|
||||
"supportsAlpha": "false",
|
||||
"isDefault": "true"
|
||||
},
|
||||
{
|
||||
"name": "RIFE 3.5",
|
||||
"desc": "Updated v3 General Model (Alpha Support) (Experimental)",
|
||||
"dir": "RIFE35",
|
||||
"name": "RIFE 3.8",
|
||||
"desc": "Updated v3 General Model",
|
||||
"dir": "RIFE38",
|
||||
"supportsAlpha": "true",
|
||||
"isDefault": "false"
|
||||
}
|
||||
},
|
||||
]
|
||||
@@ -59,15 +59,15 @@ except:
|
||||
|
||||
try:
|
||||
try:
|
||||
print(f"Trying to load v3 (new) model from {os.path.join(dname, args.model)}")
|
||||
from model.RIFE_HDv3 import Model
|
||||
print(f"Trying to load v3 (new) model using arch files from {os.path.join(dname, args.model)}")
|
||||
from arch.RIFE_HDv3 import Model
|
||||
model = Model()
|
||||
model.load_model(os.path.join(dname, args.model), -1)
|
||||
print("Loaded v3.x HD model.")
|
||||
except:
|
||||
try:
|
||||
print(f"Trying to load v3 (legacy) model from {os.path.join(dname, args.model)}")
|
||||
from model_v3_legacy.RIFE_HDv3 import Model
|
||||
from model.RIFE_HDv3 import Model
|
||||
model = Model()
|
||||
model.load_model(os.path.join(dname, args.model), -1)
|
||||
print("Loaded v3.x HD model.")
|
||||
|
||||
Reference in New Issue
Block a user