File size: 9,479 Bytes
d39b279 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 |
"""
NPR: Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection@CVPR'2024
Copyright (c) Beijing Jiaotong University and its affiliates.
Modified by Chuangchuang Tan from https://github.com/chuangchuangtan/NPR-DeepfakeDetection
"""
import torch.nn as nn
import torch
import torch.utils.model_zoo as model_zoo
from torch.nn import functional as F
from typing import Any, cast, Dict, List, Optional, Union
import numpy as np
__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
'resnet152']
model_urls = {
'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
}
def conv3x3(in_planes, out_planes, stride=1):
"""3x3 convolution with padding"""
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=1, bias=False)
def conv1x1(in_planes, out_planes, stride=1):
"""1x1 convolution"""
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(Bottleneck, self).__init__()
self.conv1 = conv1x1(inplanes, planes)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = conv3x3(planes, planes, stride)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = conv1x1(planes, planes * self.expansion)
self.bn3 = nn.BatchNorm2d(planes * self.expansion)
self.relu = nn.ReLU(inplace=True)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
out = self.conv3(out)
out = self.bn3(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, layers, num_classes=1, zero_init_residual=False):
super(ResNet, self).__init__()
self.unfoldSize = 2
self.unfoldIndex = 0
assert self.unfoldSize > 1
assert -1 < self.unfoldIndex and self.unfoldIndex < self.unfoldSize*self.unfoldSize
self.inplanes = 64
self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=2, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64 , layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
# self.fc1 = nn.Linear(512 * block.expansion, 1)
self.fc1 = nn.Linear(512, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
# Zero-initialize the last BN in each residual branch,
# so that the residual branch starts with zeros, and each residual block behaves like an identity.
# This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
if zero_init_residual:
for m in self.modules():
if isinstance(m, Bottleneck):
nn.init.constant_(m.bn3.weight, 0)
elif isinstance(m, BasicBlock):
nn.init.constant_(m.bn2.weight, 0)
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
conv1x1(self.inplanes, planes * block.expansion, stride),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for _ in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def interpolate(self, img, factor):
return F.interpolate(F.interpolate(img, scale_factor=factor, mode='nearest', recompute_scale_factor=True), scale_factor=1/factor, mode='nearest', recompute_scale_factor=True)
def forward(self, x):
# n,c,w,h = x.shape
# if -1*w%2 != 0: x = x[:,:,:w%2*-1,: ]
# if -1*h%2 != 0: x = x[:,:,: ,:h%2*-1]
# factor = 0.5
# x_half = F.interpolate(x, scale_factor=factor, mode='nearest', recompute_scale_factor=True)
# x_re = F.interpolate(x_half, scale_factor=1/factor, mode='nearest', recompute_scale_factor=True)
# NPR = x - x_re
# n,c,w,h = x.shape
# if w%2 == 1 : x = x[:,:,:-1,:]
# if h%2 == 1 : x = x[:,:,:,:-1]
b, t, _, h, w = x.shape
x = x.view(b * t, 3, h, w)
NPR = x - self.interpolate(x, 0.5)
x = self.conv1(NPR*2.0/3.0)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.fc1(x)
x = x.view(b, t, -1)
x = x.mean(1)
return x
def infer(self, x):
# n,c,w,h = x.shape
# if -1*w%2 != 0: x = x[:,:,:w%2*-1,: ]
# if -1*h%2 != 0: x = x[:,:,: ,:h%2*-1]
# factor = 0.5
# x_half = F.interpolate(x, scale_factor=factor, mode='nearest', recompute_scale_factor=True)
# x_re = F.interpolate(x_half, scale_factor=1/factor, mode='nearest', recompute_scale_factor=True)
# NPR = x - x_re
# n,c,w,h = x.shape
# if w%2 == 1 : x = x[:,:,:-1,:]
# if h%2 == 1 : x = x[:,:,:,:-1]
b, t, _, h, w = x.shape
x = x.view(b * t, 3, h, w)
NPR = x - self.interpolate(x, 0.5)
x = self.conv1(NPR*2.0/3.0)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.fc1(x)
x = x.view(b, t, -1)
x = x.mean(1)
return x
def resnet18_npr(pretrained=False, **kwargs):
"""Constructs a ResNet-18 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
return model
def resnet34_npr(pretrained=False, **kwargs):
"""Constructs a ResNet-34 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet34']))
return model
def resnet50_npr(pretrained=False, **kwargs):
"""Constructs a ResNet-50 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
if pretrained:
model_state = torch.load('/ossfs/workspace/aigc_video/weights/resnet50-19c8e357.pth')
model.load_state_dict(model_state, strict=False)
return model
def resnet101_npr(pretrained=False, **kwargs):
"""Constructs a ResNet-101 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
return model
def resnet152_npr(pretrained=False, **kwargs):
"""Constructs a ResNet-152 model.
Args:
pretrained (bool): If True, returns a model pre-trained on ImageNet
"""
model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
if pretrained:
model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
return model
|