stuff and more stuff
This commit is contained in:
DeepBeepMeep
133
postprocessing/rife/IFNet_HDv3.py
Normal file
133
postprocessing/rife/IFNet_HDv3.py
Normal file
@@ -0,0 +1,133 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
# from ..model.warplayer import warp
|
||||
|
||||
# device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||
|
||||
backwarp_tenGrid = {}
|
||||
|
||||
def warp(tenInput, tenFlow, device):
|
||||
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)
|
||||
|
||||
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)
|
||||
)
|
||||
|
||||
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(nn.Module):
|
||||
def __init__(self):
|
||||
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)
|
||||
# self.contextnet = Contextnet()
|
||||
# self.unet = Unet()
|
||||
|
||||
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], device= flow.device)
|
||||
warped_img1 = warp(img1, flow[:, 2:4], device= flow.device)
|
||||
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
|
||||
84
postprocessing/rife/RIFE_HDv3.py
Normal file
84
postprocessing/rife/RIFE_HDv3.py
Normal file
@@ -0,0 +1,84 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import numpy as np
|
||||
from torch.optim import AdamW
|
||||
import torch.optim as optim
|
||||
import itertools
|
||||
from torch.nn.parallel import DistributedDataParallel as DDP
|
||||
from .IFNet_HDv3 import *
|
||||
import torch.nn.functional as F
|
||||
# from ..model.loss import *
|
||||
|
||||
# device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||
|
||||
class Model:
|
||||
def __init__(self, local_rank=-1):
|
||||
self.flownet = IFNet()
|
||||
# self.device()
|
||||
# self.optimG = AdamW(self.flownet.parameters(), lr=1e-6, weight_decay=1e-4)
|
||||
# self.epe = EPE()
|
||||
# self.vgg = VGGPerceptualLoss().to(device)
|
||||
# self.sobel = SOBEL()
|
||||
if local_rank != -1:
|
||||
self.flownet = DDP(self.flownet, device_ids=[local_rank], output_device=local_rank)
|
||||
|
||||
def train(self):
|
||||
self.flownet.train()
|
||||
|
||||
def eval(self):
|
||||
self.flownet.eval()
|
||||
|
||||
def to(self, device):
|
||||
self.flownet.to(device)
|
||||
|
||||
def load_model(self, path, rank=0, device = "cuda"):
|
||||
self.device = device
|
||||
def convert(param):
|
||||
if rank == -1:
|
||||
return {
|
||||
k.replace("module.", ""): v
|
||||
for k, v in param.items()
|
||||
if "module." in k
|
||||
}
|
||||
else:
|
||||
return param
|
||||
self.flownet.load_state_dict(convert(torch.load(path, map_location=device)))
|
||||
|
||||
def save_model(self, path, rank=0):
|
||||
if rank == 0:
|
||||
torch.save(self.flownet.state_dict(),'{}/flownet.pkl'.format(path))
|
||||
|
||||
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.flownet(imgs, scale_list)
|
||||
return merged[2]
|
||||
|
||||
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
|
||||
img0 = imgs[:, :3]
|
||||
img1 = imgs[:, 3:]
|
||||
if training:
|
||||
self.train()
|
||||
else:
|
||||
self.eval()
|
||||
scale = [4, 2, 1]
|
||||
flow, mask, merged = self.flownet(torch.cat((imgs, gt), 1), scale=scale, training=training)
|
||||
loss_l1 = (merged[2] - gt).abs().mean()
|
||||
loss_smooth = self.sobel(flow[2], flow[2]*0).mean()
|
||||
# loss_vgg = self.vgg(merged[2], gt)
|
||||
if training:
|
||||
self.optimG.zero_grad()
|
||||
loss_G = loss_cons + loss_smooth * 0.1
|
||||
loss_G.backward()
|
||||
self.optimG.step()
|
||||
else:
|
||||
flow_teacher = flow[2]
|
||||
return merged[2], {
|
||||
'mask': mask,
|
||||
'flow': flow[2][:, :2],
|
||||
'loss_l1': loss_l1,
|
||||
'loss_cons': loss_cons,
|
||||
'loss_smooth': loss_smooth,
|
||||
}
|
||||
119
postprocessing/rife/inference.py
Normal file
119
postprocessing/rife/inference.py
Normal file
@@ -0,0 +1,119 @@
|
||||
import os
|
||||
import torch
|
||||
from torch.nn import functional as F
|
||||
# from .model.pytorch_msssim import ssim_matlab
|
||||
from .ssim import ssim_matlab
|
||||
|
||||
from .RIFE_HDv3 import Model
|
||||
|
||||
def get_frame(frames, frame_no):
|
||||
if frame_no >= frames.shape[1]:
|
||||
return None
|
||||
frame = (frames[:, frame_no] + 1) /2
|
||||
frame = frame.clip(0., 1.)
|
||||
return frame
|
||||
|
||||
def add_frame(frames, frame, h, w):
|
||||
frame = (frame * 2) - 1
|
||||
frame = frame.clip(-1., 1.)
|
||||
frame = frame.squeeze(0)
|
||||
frame = frame[:, :h, :w]
|
||||
frame = frame.unsqueeze(1)
|
||||
frames.append(frame.cpu())
|
||||
|
||||
def process_frames(model, device, frames, exp):
|
||||
pos = 0
|
||||
output_frames = []
|
||||
|
||||
lastframe = get_frame(frames, 0)
|
||||
_, h, w = lastframe.shape
|
||||
scale = 1
|
||||
fp16 = False
|
||||
|
||||
def make_inference(I0, I1, n):
|
||||
middle = model.inference(I0, I1, scale)
|
||||
if n == 1:
|
||||
return [middle]
|
||||
first_half = make_inference(I0, middle, n=n//2)
|
||||
second_half = make_inference(middle, I1, n=n//2)
|
||||
if n%2:
|
||||
return [*first_half, middle, *second_half]
|
||||
else:
|
||||
return [*first_half, *second_half]
|
||||
|
||||
tmp = max(32, int(32 / scale))
|
||||
ph = ((h - 1) // tmp + 1) * tmp
|
||||
pw = ((w - 1) // tmp + 1) * tmp
|
||||
padding = (0, pw - w, 0, ph - h)
|
||||
|
||||
def pad_image(img):
|
||||
if(fp16):
|
||||
return F.pad(img, padding).half()
|
||||
else:
|
||||
return F.pad(img, padding)
|
||||
|
||||
I1 = lastframe.to(device, non_blocking=True).unsqueeze(0)
|
||||
I1 = pad_image(I1)
|
||||
temp = None # save lastframe when processing static frame
|
||||
|
||||
while True:
|
||||
if temp is not None:
|
||||
frame = temp
|
||||
temp = None
|
||||
else:
|
||||
pos += 1
|
||||
frame = get_frame(frames, pos)
|
||||
if frame is None:
|
||||
break
|
||||
I0 = I1
|
||||
I1 = frame.to(device, non_blocking=True).unsqueeze(0)
|
||||
I1 = pad_image(I1)
|
||||
I0_small = F.interpolate(I0, (32, 32), mode='bilinear', align_corners=False)
|
||||
I1_small = F.interpolate(I1, (32, 32), mode='bilinear', align_corners=False)
|
||||
ssim = ssim_matlab(I0_small[:, :3], I1_small[:, :3])
|
||||
|
||||
break_flag = False
|
||||
if ssim > 0.996 or pos > 100:
|
||||
pos += 1
|
||||
frame = get_frame(frames, pos)
|
||||
if frame is None:
|
||||
break_flag = True
|
||||
frame = lastframe
|
||||
else:
|
||||
temp = frame
|
||||
I1 = frame.to(device, non_blocking=True).unsqueeze(0)
|
||||
I1 = pad_image(I1)
|
||||
I1 = model.inference(I0, I1, scale)
|
||||
I1_small = F.interpolate(I1, (32, 32), mode='bilinear', align_corners=False)
|
||||
ssim = ssim_matlab(I0_small[:, :3], I1_small[:, :3])
|
||||
frame = I1[0][:, :h, :w]
|
||||
|
||||
if ssim < 0.2:
|
||||
output = []
|
||||
for _ in range((2 ** exp) - 1):
|
||||
output.append(I0)
|
||||
else:
|
||||
output = make_inference(I0, I1, 2**exp-1) if exp else []
|
||||
|
||||
add_frame(output_frames, lastframe, h, w)
|
||||
for mid in output:
|
||||
add_frame(output_frames, mid, h, w)
|
||||
lastframe = frame
|
||||
if break_flag:
|
||||
break
|
||||
|
||||
add_frame(output_frames, lastframe, h, w)
|
||||
return torch.cat( output_frames, dim=1)
|
||||
|
||||
def temporal_interpolation(model_path, frames, exp, device ="cuda"):
|
||||
|
||||
model = Model()
|
||||
model.load_model(model_path, -1, device=device)
|
||||
|
||||
model.eval()
|
||||
model.to(device=device)
|
||||
|
||||
with torch.no_grad():
|
||||
output = process_frames(model, device, frames.float(), exp)
|
||||
|
||||
return output
|
||||
200
postprocessing/rife/ssim.py
Normal file
200
postprocessing/rife/ssim.py
Normal file
@@ -0,0 +1,200 @@
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
from math import exp
|
||||
import numpy as np
|
||||
|
||||
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||
|
||||
def gaussian(window_size, sigma):
|
||||
gauss = torch.Tensor([exp(-(x - window_size//2)**2/float(2*sigma**2)) for x in range(window_size)])
|
||||
return gauss/gauss.sum()
|
||||
|
||||
|
||||
def create_window(window_size, channel=1):
|
||||
_1D_window = gaussian(window_size, 1.5).unsqueeze(1)
|
||||
_2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0).to(device)
|
||||
window = _2D_window.expand(channel, 1, window_size, window_size).contiguous()
|
||||
return window
|
||||
|
||||
def create_window_3d(window_size, channel=1):
|
||||
_1D_window = gaussian(window_size, 1.5).unsqueeze(1)
|
||||
_2D_window = _1D_window.mm(_1D_window.t())
|
||||
_3D_window = _2D_window.unsqueeze(2) @ (_1D_window.t())
|
||||
window = _3D_window.expand(1, channel, window_size, window_size, window_size).contiguous().to(device)
|
||||
return window
|
||||
|
||||
|
||||
def ssim(img1, img2, window_size=11, window=None, size_average=True, full=False, val_range=None):
|
||||
# Value range can be different from 255. Other common ranges are 1 (sigmoid) and 2 (tanh).
|
||||
if val_range is None:
|
||||
if torch.max(img1) > 128:
|
||||
max_val = 255
|
||||
else:
|
||||
max_val = 1
|
||||
|
||||
if torch.min(img1) < -0.5:
|
||||
min_val = -1
|
||||
else:
|
||||
min_val = 0
|
||||
L = max_val - min_val
|
||||
else:
|
||||
L = val_range
|
||||
|
||||
padd = 0
|
||||
(_, channel, height, width) = img1.size()
|
||||
if window is None:
|
||||
real_size = min(window_size, height, width)
|
||||
window = create_window(real_size, channel=channel).to(img1.device)
|
||||
|
||||
# mu1 = F.conv2d(img1, window, padding=padd, groups=channel)
|
||||
# mu2 = F.conv2d(img2, window, padding=padd, groups=channel)
|
||||
mu1 = F.conv2d(F.pad(img1, (5, 5, 5, 5), mode='replicate'), window, padding=padd, groups=channel)
|
||||
mu2 = F.conv2d(F.pad(img2, (5, 5, 5, 5), mode='replicate'), window, padding=padd, groups=channel)
|
||||
|
||||
mu1_sq = mu1.pow(2)
|
||||
mu2_sq = mu2.pow(2)
|
||||
mu1_mu2 = mu1 * mu2
|
||||
|
||||
sigma1_sq = F.conv2d(F.pad(img1 * img1, (5, 5, 5, 5), 'replicate'), window, padding=padd, groups=channel) - mu1_sq
|
||||
sigma2_sq = F.conv2d(F.pad(img2 * img2, (5, 5, 5, 5), 'replicate'), window, padding=padd, groups=channel) - mu2_sq
|
||||
sigma12 = F.conv2d(F.pad(img1 * img2, (5, 5, 5, 5), 'replicate'), window, padding=padd, groups=channel) - mu1_mu2
|
||||
|
||||
C1 = (0.01 * L) ** 2
|
||||
C2 = (0.03 * L) ** 2
|
||||
|
||||
v1 = 2.0 * sigma12 + C2
|
||||
v2 = sigma1_sq + sigma2_sq + C2
|
||||
cs = torch.mean(v1 / v2) # contrast sensitivity
|
||||
|
||||
ssim_map = ((2 * mu1_mu2 + C1) * v1) / ((mu1_sq + mu2_sq + C1) * v2)
|
||||
|
||||
if size_average:
|
||||
ret = ssim_map.mean()
|
||||
else:
|
||||
ret = ssim_map.mean(1).mean(1).mean(1)
|
||||
|
||||
if full:
|
||||
return ret, cs
|
||||
return ret
|
||||
|
||||
|
||||
def ssim_matlab(img1, img2, window_size=11, window=None, size_average=True, full=False, val_range=None):
|
||||
# Value range can be different from 255. Other common ranges are 1 (sigmoid) and 2 (tanh).
|
||||
if val_range is None:
|
||||
if torch.max(img1) > 128:
|
||||
max_val = 255
|
||||
else:
|
||||
max_val = 1
|
||||
|
||||
if torch.min(img1) < -0.5:
|
||||
min_val = -1
|
||||
else:
|
||||
min_val = 0
|
||||
L = max_val - min_val
|
||||
else:
|
||||
L = val_range
|
||||
|
||||
padd = 0
|
||||
(_, _, height, width) = img1.size()
|
||||
if window is None:
|
||||
real_size = min(window_size, height, width)
|
||||
window = create_window_3d(real_size, channel=1).to(img1.device)
|
||||
# Channel is set to 1 since we consider color images as volumetric images
|
||||
|
||||
img1 = img1.unsqueeze(1)
|
||||
img2 = img2.unsqueeze(1)
|
||||
|
||||
mu1 = F.conv3d(F.pad(img1, (5, 5, 5, 5, 5, 5), mode='replicate'), window, padding=padd, groups=1)
|
||||
mu2 = F.conv3d(F.pad(img2, (5, 5, 5, 5, 5, 5), mode='replicate'), window, padding=padd, groups=1)
|
||||
|
||||
mu1_sq = mu1.pow(2)
|
||||
mu2_sq = mu2.pow(2)
|
||||
mu1_mu2 = mu1 * mu2
|
||||
|
||||
sigma1_sq = F.conv3d(F.pad(img1 * img1, (5, 5, 5, 5, 5, 5), 'replicate'), window, padding=padd, groups=1) - mu1_sq
|
||||
sigma2_sq = F.conv3d(F.pad(img2 * img2, (5, 5, 5, 5, 5, 5), 'replicate'), window, padding=padd, groups=1) - mu2_sq
|
||||
sigma12 = F.conv3d(F.pad(img1 * img2, (5, 5, 5, 5, 5, 5), 'replicate'), window, padding=padd, groups=1) - mu1_mu2
|
||||
|
||||
C1 = (0.01 * L) ** 2
|
||||
C2 = (0.03 * L) ** 2
|
||||
|
||||
v1 = 2.0 * sigma12 + C2
|
||||
v2 = sigma1_sq + sigma2_sq + C2
|
||||
cs = torch.mean(v1 / v2) # contrast sensitivity
|
||||
|
||||
ssim_map = ((2 * mu1_mu2 + C1) * v1) / ((mu1_sq + mu2_sq + C1) * v2)
|
||||
|
||||
if size_average:
|
||||
ret = ssim_map.mean()
|
||||
else:
|
||||
ret = ssim_map.mean(1).mean(1).mean(1)
|
||||
|
||||
if full:
|
||||
return ret, cs
|
||||
return ret
|
||||
|
||||
|
||||
def msssim(img1, img2, window_size=11, size_average=True, val_range=None, normalize=False):
|
||||
device = img1.device
|
||||
weights = torch.FloatTensor([0.0448, 0.2856, 0.3001, 0.2363, 0.1333]).to(device)
|
||||
levels = weights.size()[0]
|
||||
mssim = []
|
||||
mcs = []
|
||||
for _ in range(levels):
|
||||
sim, cs = ssim(img1, img2, window_size=window_size, size_average=size_average, full=True, val_range=val_range)
|
||||
mssim.append(sim)
|
||||
mcs.append(cs)
|
||||
|
||||
img1 = F.avg_pool2d(img1, (2, 2))
|
||||
img2 = F.avg_pool2d(img2, (2, 2))
|
||||
|
||||
mssim = torch.stack(mssim)
|
||||
mcs = torch.stack(mcs)
|
||||
|
||||
# Normalize (to avoid NaNs during training unstable models, not compliant with original definition)
|
||||
if normalize:
|
||||
mssim = (mssim + 1) / 2
|
||||
mcs = (mcs + 1) / 2
|
||||
|
||||
pow1 = mcs ** weights
|
||||
pow2 = mssim ** weights
|
||||
# From Matlab implementation https://ece.uwaterloo.ca/~z70wang/research/iwssim/
|
||||
output = torch.prod(pow1[:-1] * pow2[-1])
|
||||
return output
|
||||
|
||||
|
||||
# Classes to re-use window
|
||||
class SSIM(torch.nn.Module):
|
||||
def __init__(self, window_size=11, size_average=True, val_range=None):
|
||||
super(SSIM, self).__init__()
|
||||
self.window_size = window_size
|
||||
self.size_average = size_average
|
||||
self.val_range = val_range
|
||||
|
||||
# Assume 3 channel for SSIM
|
||||
self.channel = 3
|
||||
self.window = create_window(window_size, channel=self.channel)
|
||||
|
||||
def forward(self, img1, img2):
|
||||
(_, channel, _, _) = img1.size()
|
||||
|
||||
if channel == self.channel and self.window.dtype == img1.dtype:
|
||||
window = self.window
|
||||
else:
|
||||
window = create_window(self.window_size, channel).to(img1.device).type(img1.dtype)
|
||||
self.window = window
|
||||
self.channel = channel
|
||||
|
||||
_ssim = ssim(img1, img2, window=window, window_size=self.window_size, size_average=self.size_average)
|
||||
dssim = (1 - _ssim) / 2
|
||||
return dssim
|
||||
|
||||
class MSSSIM(torch.nn.Module):
|
||||
def __init__(self, window_size=11, size_average=True, channel=3):
|
||||
super(MSSSIM, self).__init__()
|
||||
self.window_size = window_size
|
||||
self.size_average = size_average
|
||||
self.channel = channel
|
||||
|
||||
def forward(self, img1, img2):
|
||||
return msssim(img1, img2, window_size=self.window_size, size_average=self.size_average)
|
||||
Reference in New Issue
Block a user