model.py

import torch.nn as nn

class Net_28(nn.Module):
    def __init__(self, in_channels, num_classes):
        super(Net_28, self).__init__()

        self.layer1 = nn.Sequential(
            nn.Conv2d(in_channels, 16, kernel_size=3),
            nn.GroupNorm(4, 16),
            nn.ReLU())

        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 16, kernel_size=3),
            nn.GroupNorm(4, 16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))

        self.layer3 = nn.Sequential(
            nn.Conv2d(16, 64, kernel_size=3),
            nn.GroupNorm(16, 64),
            nn.ReLU())
        
        self.layer4 = nn.Sequential(
            nn.Conv2d(64, 64, kernel_size=3),
            nn.GroupNorm(16, 64),
            nn.ReLU())

        self.layer5 = nn.Sequential(
            nn.Conv2d(64, 64, kernel_size=3, padding=1),
            nn.GroupNorm(16, 64),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))

        self.fc = nn.Sequential(
            nn.Linear(64 * 4 * 4, 128),
            nn.ReLU(),
            nn.Linear(128, 128),
            nn.ReLU(),
            nn.Linear(128, num_classes))

    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = self.layer5(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

class Net_224(nn.Module):
    def __init__(self, in_channels, num_classes):
        super(Net_224, self).__init__()

        self.layer1 = nn.Sequential(
            nn.Conv2d(in_channels, 16, kernel_size=3),
            nn.GroupNorm(4, 16),
            nn.ReLU())

        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 16, kernel_size=3),
            nn.GroupNorm(4, 16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))

        self.layer3 = nn.Sequential(
            nn.Conv2d(16, 64, kernel_size=3),
            nn.GroupNorm(16, 64),
            nn.ReLU())

        self.layer4 = nn.Sequential(
            nn.Conv2d(64, 64, kernel_size=3),
            nn.GroupNorm(16, 64),
            nn.ReLU())

        self.layer5 = nn.Sequential(
            nn.Conv2d(64, 64, kernel_size=3, padding=1),
            nn.GroupNorm(16, 64),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))

        self.layer6 = nn.Sequential(
            nn.Conv2d(64, 128, kernel_size=3),
            nn.GroupNorm(32, 128),
            nn.ReLU())

        self.layer7 = nn.Sequential(
            nn.Conv2d(128, 128, kernel_size=3, padding=1),
            nn.GroupNorm(32, 128),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))

        self.fc = nn.Sequential(
            nn.Linear(128 * 25 * 25, 256),
            nn.ReLU(),
            nn.Linear(256, 256),
            nn.ReLU(),
            nn.Linear(256, num_classes))

    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = self.layer5(x)
        x = self.layer6(x)
        x = self.layer7(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x