AutoEncoder_model.py

import torch.nn as nn
import torch
import numpy as np
from torchvision import transforms as T



class ImprovedConvAutoencoder(nn.Module):
    def __init__(self):
        super().__init__()
        # encoder
        self.conv1 = nn.Sequential(
            nn.Conv2d(1, 32, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(32),
            nn.ReLU()
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(64),
            nn.ReLU()
        )
        self.conv3 = nn.Sequential(
            nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(128),
            nn.ReLU()
        )

        # additional encoder layer
        self.conv4 = nn.Sequential(
            nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(256),
            nn.ReLU()
        )

        # decoder
        # additional decoder layer
        self.deconv4 = nn.Sequential(
            nn.ConvTranspose2d(256, 128, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(128),
            nn.ReLU()
        )

        self.deconv1 = nn.Sequential(
            nn.ConvTranspose2d(128, 64, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(64),
            nn.ReLU()
        )
        self.deconv2 = nn.Sequential(
            nn.ConvTranspose2d(64, 32, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(32),
            nn.ReLU()
        )
        self.deconv3 = nn.Sequential(
            nn.ConvTranspose2d(32, 1, kernel_size=3, stride=1, padding=1),
            nn.Sigmoid()
        )

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = self.conv3(x)
        x = self.conv4(x)
        x = self.deconv4(x)
        x = self.deconv1(x)
        x = self.deconv2(x)
        x = self.deconv3(x)
        return x


def preprocess_image(image):
    preprocess = T.Compose([
        T.Resize((640, 640)),
        T.ToTensor(),
    ])
    img_tensor = preprocess(image).unsqueeze(0)
    return img_tensor