from __future__ import annotations

import torch
from torch import nn


class LeNet(nn.Module):
    """LeNet-5 for 1x32x32."""

    def __init__(self, num_classes: int = 10):
        super().__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(1, 6, kernel_size=5, stride=1, padding=0),
            nn.Sigmoid(),
            nn.MaxPool2d(kernel_size=2, stride=2),
            nn.Conv2d(6, 16, kernel_size=5, stride=1, padding=0),
            nn.Sigmoid(),
            nn.MaxPool2d(kernel_size=2, stride=2),
        )
        self.fc = nn.Sequential(
            nn.Linear(16 * 5 * 5, 120),
            nn.Sigmoid(),
            nn.Linear(120, 84),
            nn.Sigmoid(),
            nn.Linear(84, num_classes),
        )

    def forward(self, img: torch.Tensor) -> torch.Tensor:
        x = self.conv(img)
        x = x.view(img.shape[0], -1)
        return self.fc(x)


class AlexNet(nn.Module):
    """AlexNet for 3x224x224."""

    def __init__(self, num_classes: int = 1000):
        super().__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 96, kernel_size=11, stride=4, padding=2),
            nn.ReLU(inplace=True),
            nn.LocalResponseNorm(size=5, alpha=1e-4, beta=0.75, k=2.0),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(96, 256, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),
            nn.LocalResponseNorm(size=5, alpha=1e-4, beta=0.75, k=2.0),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(256, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
        )
        self.avgpool = nn.AdaptiveAvgPool2d((6, 6))
        self.classifier = nn.Sequential(
            nn.Dropout(p=0.5),
            nn.Linear(256 * 6 * 6, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(p=0.5),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, num_classes),
        )

    def forward(self, img: torch.Tensor) -> torch.Tensor:
        x = self.features(img)
        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        return self.classifier(x)


if __name__ == "__main__":
    print("[LeNet]", LeNet(num_classes=10)(torch.randn(2, 1, 32, 32)).shape)
    print("[AlexNet]", AlexNet(num_classes=1000)(torch.randn(2, 3, 224, 224)).shape)