Mirrors/flowframes
1
0
Fork 0
mirror of https://github.com/n00mkrad/flowframes.git synced 2026-02-24 12:12:36 +01:00
Code Issues Packages Projects Releases Wiki Activity

Revert to old UHD mode (RIFE CUDA)

Browse Source
This commit is contained in:
N00MKRAD
2021-03-02 22:54:30 +01:00
parent 9ba522f890
commit 504242dca7
6 changed files with 44 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
Code/OS/AiProcess.cs
View File

@@ -125,11 +125,12 @@ namespace Flowframes
{
//bool parallel = false;
string outPath = Path.Combine(inPath.GetParentDir(), outDir);
string uhdStr = await InterpolateUtils.UseUHD() ? "--UHD" : "";
string wthreads = $"--wthreads {2 * (int)interpFactor}";
string rbuffer = $"--rbuffer {Config.GetInt("rifeCudaBufferSize", 200)}";
string scale = $"--scale {Config.GetFloat("rifeCudaScale", 1.0f).ToStringDot()}";
//string scale = $"--scale {Config.GetFloat("rifeCudaScale", 1.0f).ToStringDot()}";
string prec = Config.GetBool("rifeCudaFp16") ? "--fp16" : "";
string args = $" --input {inPath.Wrap()} --output {outDir} --model {mdl} --exp {(int)Math.Log(interpFactor, 2)} {scale} {wthreads} {rbuffer} {prec}";
string args = $" --input {inPath.Wrap()} --output {outDir} --model {mdl} --exp {(int)Math.Log(interpFactor, 2)} {uhdStr} {wthreads} {rbuffer} {prec}";
// if (parallel) args = $" --input {inPath.Wrap()} --output {outPath} --model {mdl} --factor {interpFactor}";
// if (parallel) script = "rife-parallel.py";
@@ -138,7 +139,7 @@ namespace Flowframes
SetProgressCheck(Path.Combine(Interpolate.current.tempFolder, outDir), interpFactor);
rifePy.StartInfo.Arguments = $"{OSUtils.GetCmdArg()} cd /D {PkgUtils.GetPkgFolder(Packages.rifeCuda).Wrap()} & " +
$"set CUDA_VISIBLE_DEVICES={Config.Get("torchGpus")} & {Python.GetPyCmd()} {script} {args}";
Logger.Log($"Running RIFE (CUDA)...".TrimWhitespaces(), false);
Logger.Log($"Running RIFE (CUDA){(await InterpolateUtils.UseUHD() ? " (UHD Mode)" : "")}...", false);
Logger.Log("cmd.exe " + rifePy.StartInfo.Arguments, true);
if (!OSUtils.ShowHiddenCmd())

11
Pkgs/rife-cuda/model/IFNet_HD.py
View File

@@ -91,9 +91,12 @@ class IFNet(nn.Module):
self.block2 = IFBlock(8, scale=2, c=96)
self.block3 = IFBlock(8, scale=1, c=48)
def forward(self, x, scale=1.0):
x = F.interpolate(x, scale_factor=0.5 * scale, mode="bilinear",
align_corners=False)
def forward(self, x, UHD=False):
if UHD:
x = F.interpolate(x, scale_factor=0.25, mode="bilinear", align_corners=False)
else:
x = F.interpolate(x, scale_factor=0.5, mode="bilinear",
align_corners=False)
flow0 = self.block0(x)
F1 = flow0
warped_img0 = warp(x[:, :3], F1)
@@ -108,8 +111,6 @@ class IFNet(nn.Module):
warped_img1 = warp(x[:, 3:], -F3)
flow3 = self.block3(torch.cat((warped_img0, warped_img1, F3), 1))
F4 = (flow0 + flow1 + flow2 + flow3)
F4 = F.interpolate(F4, scale_factor=1 / scale, mode="bilinear",
align_corners=False) / scale
return F4, [F1, F2, F3, F4]
if __name__ == '__main__':

27
Pkgs/rife-cuda/model/IFNet_HDv2.py
View File

@@ -39,19 +39,18 @@ class IFBlock(nn.Module):
)
self.conv1 = nn.ConvTranspose2d(2*c, 4, 4, 2, 1)
def forward(self, x, scale=1.0):
infer_scale = self.scale / scale
if infer_scale != 1.0:
x = F.interpolate(x, scale_factor=1. / infer_scale, mode="bilinear",
def forward(self, x):
if self.scale != 1:
x = F.interpolate(x, scale_factor=1. / self.scale, mode="bilinear",
align_corners=False)
x = self.conv0(x)
x = self.convblock(x)
x = self.conv1(x)
flow = x
if infer_scale != 1.0:
flow = F.interpolate(flow, scale_factor=infer_scale, mode="bilinear",
align_corners=False)
return flow / scale
if self.scale != 1:
flow = F.interpolate(flow, scale_factor=self.scale, mode="bilinear",
align_corners=False)
return flow
class IFNet(nn.Module):
@@ -62,23 +61,25 @@ class IFNet(nn.Module):
self.block2 = IFBlock(10, scale=2, c=96)
self.block3 = IFBlock(10, scale=1, c=48)
def forward(self, x, scale=1.0):
flow0 = self.block0(x, scale)
def forward(self, x, UHD=False):
if UHD:
x = F.interpolate(x, scale_factor=0.5, mode="bilinear", align_corners=False)
flow0 = self.block0(x)
F1 = flow0
F1_large = F.interpolate(F1, scale_factor=2.0, mode="bilinear", align_corners=False, recompute_scale_factor=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, F1_large), 1), scale)
flow1 = self.block1(torch.cat((warped_img0, warped_img1, F1_large), 1))
F2 = (flow0 + flow1)
F2_large = F.interpolate(F2, scale_factor=2.0, mode="bilinear", align_corners=False, recompute_scale_factor=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, F2_large), 1), scale)
flow2 = self.block2(torch.cat((warped_img0, warped_img1, F2_large), 1))
F3 = (flow0 + flow1 + flow2)
F3_large = F.interpolate(F3, scale_factor=2.0, mode="bilinear", align_corners=False, recompute_scale_factor=False) * 2.0
warped_img0 = warp(x[:, :3], F3_large[:, :2])
warped_img1 = warp(x[:, 3:], F3_large[:, 2:4])
flow3 = self.block3(torch.cat((warped_img0, warped_img1, F3_large), 1), scale)
flow3 = self.block3(torch.cat((warped_img0, warped_img1, F3_large), 1))
F4 = (flow0 + flow1 + flow2 + flow3)
return F4, [F1, F2, F3, F4]

10
Pkgs/rife-cuda/model/RIFE_HD.py
View File

@@ -188,9 +188,11 @@ class Model:
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):
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)
c1 = self.contextnet(img1, -flow)
flow = F.interpolate(flow, scale_factor=2.0, mode="bilinear",
@@ -207,10 +209,10 @@ class Model:
else:
return pred
def inference(self, img0, img1, scale=1.0):
def inference(self, img0, img1, UHD=False):
imgs = torch.cat((img0, img1), 1)
flow, _ = self.flownet(imgs, scale)
return self.predict(imgs, flow, training=False)
flow, _ = self.flownet(imgs, UHD)
return self.predict(imgs, flow, training=False, UHD=UHD)
def update(self, imgs, gt, learning_rate=0, mul=1, training=True, flow_gt=None):
for param_group in self.optimG.param_groups:

10
Pkgs/rife-cuda/model/RIFE_HDv2.py
View File

@@ -173,9 +173,11 @@ class Model:
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):
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",
@@ -192,10 +194,10 @@ class Model:
else:
return pred
def inference(self, img0, img1, scale=1.0):
def inference(self, img0, img1, UHD=False):
imgs = torch.cat((img0, img1), 1)
flow, _ = self.flownet(imgs, scale)
return self.predict(imgs, flow, training=False)
flow, _ = self.flownet(imgs, UHD)
return self.predict(imgs, flow, training=False, UHD=UHD)
def update(self, imgs, gt, learning_rate=0, mul=1, training=True, flow_gt=None):
for param_group in self.optimG.param_groups:

13
Pkgs/rife-cuda/rife.py
View File

@@ -107,7 +107,7 @@ def build_read_buffer(user_args, read_buffer, videogen):
def make_inference(I0, I1, exp):
global model
middle = model.inference(I0, I1, args.scale)
middle = model.inference(I0, I1, args.UHD)
if exp == 1:
return [middle]
first_half = make_inference(I0, middle, exp=exp - 1)
@@ -120,10 +120,13 @@ def pad_image(img):
else:
return F.pad(img, padding)
print(f"Scale: {args.scale}")
tmp = max(32, int(32 / args.scale))
ph = ((h - 1) // tmp + 1) * tmp
pw = ((w - 1) // tmp + 1) * tmp
if args.UHD:
print("UHD mode enabled.")
ph = ((h - 1) // 64 + 1) * 64
pw = ((w - 1) // 64 + 1) * 64
else:
ph = ((h - 1) // 32 + 1) * 32
pw = ((w - 1) // 32 + 1) * 32
padding = (0, pw - w, 0, ph - h)
write_buffer = Queue(maxsize=args.rbuffer)