model.py

import torch.nn as nn
import torch.nn.functional as F
import torchvision.models as models


class LeNet(nn.Sequential):
    """
    Adaptation of LeNet that uses ReLU activations
    """

    # network architecture:
    def __init__(self, num_classes=10):
        super(LeNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, num_classes)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


class BigLeNet(nn.Sequential):
    """
    bigger adpation of LeNet that uses ReLU
    16 32
    relu
    32 16
    """

    # network architecture:
    def __init__(self, num_classes=10):
        super(BigLeNet, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=6, kernel_size=5)
        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)
        self.conv2 = nn.Conv2d(in_channels=6, out_channels=16, kernel_size=5)
        self.conv3 = nn.Conv2d(in_channels=16, out_channels=32, kernel_size=5)
        self.conv4 = nn.Conv2d(in_channels=32, out_channels=16, kernel_size=5)
        self.fc1 = nn.Linear(in_features=16 * 5 * 5, out_features=120)
        self.fc2 = nn.Linear(in_features=120, out_features=84)
        self.fc3 = nn.Linear(in_features=84, out_features=num_classes)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = F.relu(self.conv3(x))
        x = F.relu(self.conv4(x))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


def get_model(model_name: str = 'resnet18', num_classes: int = 2):
    if model_name == 'LeNet':
        return LeNet(num_classes=num_classes)

    elif model_name == 'BigLeNet':
        return BigLeNet(num_classes=num_classes)

    else:
        try:
            model = getattr(models, model_name)(pretrained=True)
            in_features = model._modules['fc'].in_features
            model._modules['fc'] = nn.Linear(in_features=in_features, out_features=num_classes, bias=True)
            return model
        except Exception as e:
            print(e)