mirror of
https://github.com/vladmandic/automatic
synced 2026-09-18 16:54:33 +02:00
chore(rife): drop the two vendored v3 modules the v4.25 upgrade orphaned
dc4c58d0 replaced the vendored RIFE with Practical-RIFE v4.25 and gave
warp() an explicit (tenFlow_div, backwarp_tenGrid) signature, but left
refine.py behind: its four warp(x, flow) calls no longer match, and
nothing imports the module. loss.py holds the EPE/SOBEL training
scaffolding the same commit says it dropped, and is likewise unused.This commit is contained in:
Anai-Guo
@@ -1,121 +0,0 @@
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import torchvision.models as models
|
||||
from modules import devices
|
||||
|
||||
|
||||
class EPE(nn.Module):
|
||||
def __init__(self):
|
||||
super().__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().__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(devices.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().__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(devices.device)
|
||||
self.kernelY = self.kernelY.unsqueeze(0).unsqueeze(0).to(devices.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().__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): # pylint: disable=unused-argument
|
||||
super().__init__()
|
||||
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).to(device=devices.device)
|
||||
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
|
||||
@@ -1,90 +0,0 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
from modules.rife.warplayer import warp
|
||||
|
||||
|
||||
c = 16
|
||||
|
||||
|
||||
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)
|
||||
)
|
||||
|
||||
|
||||
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),
|
||||
)
|
||||
|
||||
|
||||
def deconv(in_planes, out_planes, kernel_size=4, stride=2, padding=1): # pylint: disable=unused-argument
|
||||
return nn.Sequential(
|
||||
torch.nn.ConvTranspose2d(in_channels=in_planes, out_channels=out_planes, kernel_size=4, stride=2, padding=1, bias=True),
|
||||
nn.LeakyReLU(0.2, True)
|
||||
)
|
||||
|
||||
|
||||
class Conv2(nn.Module):
|
||||
def __init__(self, in_planes, out_planes, stride=2):
|
||||
super().__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 Contextnet(nn.Module):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.conv1 = Conv2(3, 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.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 Unet(nn.Module):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.down0 = Conv2(17, 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.Conv2d(c, 3, 3, 1, 1)
|
||||
|
||||
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), 1))
|
||||
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 torch.sigmoid(x)
|
||||
Reference in New Issue
Block a user