• Search by Module
• Search by Words
• Search Projects

• Java
• Python
• JavaScript
• TypeScript
• C++
• Scala
• Blog

• Deep-SAD-PyTorch-master
  • src
    • datasets
      • cifar10.py
      • mnist.py
      • fmnist.py
      • preprocessing.py
      • __init__.py
      • main.py
      • odds.py
    • utils
      • misc.py
      • config.py
      • __init__.py
      • visualization
        • plot_images_grid.py
    • optim
      • ae_trainer.py
      • SemiDGM_trainer.py
      • vae_trainer.py
      • DeepSAD_trainer.py
      • variational.py
      • __init__.py
    • baseline_SemiDGM.py
    • baseline_isoforest.py
    • baseline_ocsvm.py
    • base
      • base_net.py
      • base_trainer.py
      • __init__.py
      • odds_dataset.py
      • torchvision_dataset.py
      • base_dataset.py
    • networks
      • cifar10_LeNet.py
      • layers
        • stochastic.py
        • standard.py
      • vae.py
      • mnist_LeNet.py
      • fmnist_LeNet.py
      • __init__.py
      • main.py
      • inference
        • distributions.py
      • mlp.py
      • dgm.py
    • baseline_ssad.py
    • DeepSAD.py
    • baselines
      • ssad.py
      • isoforest.py
      • kde.py
      • ocsvm.py
      • SemiDGM.py
      • __init__.py
      • shallow_ssad
        • ssad_convex.py
        • __init__.py
    • __init__.py
    • main.py
    • baseline_kde.py
  • LICENSE
  • log
    • .gitkeep
  • imgs
    • .gitkeep
  • data
    • .gitkeep
  • README.md
  • requirements.txt

import torch
import torch.nn as nn
import torch.nn.functional as F

from base.base_net import BaseNet


class FashionMNIST_LeNet(BaseNet):

    def __init__(self, rep_dim=64):
        super().__init__()

        self.rep_dim = rep_dim
        self.pool = nn.MaxPool2d(2, 2)

        self.conv1 = nn.Conv2d(1, 16, 5, bias=False, padding=2)
        self.bn2d1 = nn.BatchNorm2d(16, eps=1e-04, affine=False)
        self.conv2 = nn.Conv2d(16, 32, 5, bias=False, padding=2)
        self.bn2d2 = nn.BatchNorm2d(32, eps=1e-04, affine=False)
        self.fc1 = nn.Linear(32 * 7 * 7, 128, bias=False)
        self.bn1d1 = nn.BatchNorm1d(128, eps=1e-04, affine=False)
        self.fc2 = nn.Linear(128, self.rep_dim, bias=False)

    def forward(self, x):
        x = x.view(-1, 1, 28, 28)
        x = self.conv1(x)
        x = self.pool(F.leaky_relu(self.bn2d1(x)))
        x = self.conv2(x)
        x = self.pool(F.leaky_relu(self.bn2d2(x)))
        x = x.view(int(x.size(0)), -1)
        x = F.leaky_relu(self.bn1d1(self.fc1(x)))
        x = self.fc2(x)
        return x


class FashionMNIST_LeNet_Decoder(BaseNet):

    def __init__(self, rep_dim=64):
        super().__init__()

        self.rep_dim = rep_dim

        self.fc3 = nn.Linear(self.rep_dim, 128, bias=False)
        self.bn1d2 = nn.BatchNorm1d(128, eps=1e-04, affine=False)
        self.deconv1 = nn.ConvTranspose2d(8, 32, 5, bias=False, padding=2)
        self.bn2d3 = nn.BatchNorm2d(32, eps=1e-04, affine=False)
        self.deconv2 = nn.ConvTranspose2d(32, 16, 5, bias=False, padding=3)
        self.bn2d4 = nn.BatchNorm2d(16, eps=1e-04, affine=False)
        self.deconv3 = nn.ConvTranspose2d(16, 1, 5, bias=False, padding=2)

    def forward(self, x):
        x = self.bn1d2(self.fc3(x))
        x = x.view(int(x.size(0)), int(128 / 16), 4, 4)
        x = F.interpolate(F.leaky_relu(x), scale_factor=2)
        x = self.deconv1(x)
        x = F.interpolate(F.leaky_relu(self.bn2d3(x)), scale_factor=2)
        x = self.deconv2(x)
        x = F.interpolate(F.leaky_relu(self.bn2d4(x)), scale_factor=2)
        x = self.deconv3(x)
        x = torch.sigmoid(x)
        return x


class FashionMNIST_LeNet_Autoencoder(BaseNet):

    def __init__(self, rep_dim=64):
        super().__init__()

        self.rep_dim = rep_dim
        self.encoder = FashionMNIST_LeNet(rep_dim=rep_dim)
        self.decoder = FashionMNIST_LeNet_Decoder(rep_dim=rep_dim)

    def forward(self, x):
        x = self.encoder(x)
        x = self.decoder(x)
        return x