Spaces:
Sleeping
Sleeping
| import torch | |
| import torch.nn as nn | |
| from torch.nn import functional as F | |
| 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 VAEReconEncoder(nn.Module): | |
| def __init__(self, vae, block=Bottleneck): | |
| super(VAEReconEncoder, self).__init__() | |
| # Define the ResNet model | |
| self.inplanes = 64 | |
| self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=2, padding=1, bias=False) | |
| # self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False) | |
| self.bn1 = nn.BatchNorm2d(64) | |
| self.relu = nn.ReLU(inplace=True) | |
| self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) | |
| # ResNet-50 is [3, 4, 6, 3] | |
| self.layer1 = self._make_layer(block, 64 , 3) | |
| self.layer2 = self._make_layer(block, 128, 4, stride=2) | |
| # self.layer3 = self._make_layer(block, 256, 6, stride=2) | |
| # self.layer4 = self._make_layer(block, 512, 3, stride=2) | |
| self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) | |
| # Kaiming initialization | |
| 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) | |
| # Load the VAE model | |
| self.vae = vae | |
| 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 reconstruct(self, x): | |
| with torch.no_grad(): | |
| # `.sample()` means to sample a latent vector from the distribution | |
| # `.mean` means to use the mean of the distribution | |
| latent = self.vae.encode(x).latent_dist.mean | |
| decoded = self.vae.decode(latent).sample | |
| return decoded | |
| def forward(self, x): | |
| # Reconstruct | |
| x_recon = self.reconstruct(x) | |
| # Compute the artifacts | |
| x = x - x_recon | |
| # Scale the artifacts | |
| x = x / 7. * 100. | |
| # Forward pass | |
| x = self.conv1(x) | |
| 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) | |
| return x | |