import torch
import torch.nn as nn
from typing import Type, Union, List, Optional


class BasicBlock(nn.Module):
    expansion: int = 1

    def __init__(
        self,
        in_channels: int,
        out_channels: int,
        stride: int = 1,
        downsample: Optional[nn.Module] = None,
    ) -> None:
        super().__init__()
        self.conv1 = nn.Conv2d(
            in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(out_channels, out_channels,
                               kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        identity = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        if self.downsample is not None:
            identity = self.downsample(x)
        out += identity
        out = self.relu(out)
        return out


class Bottleneck(nn.Module):
    expansion: int = 4

    def __init__(
        self,
        in_channels: int,
        out_channels: int,
        stride: int = 1,
        downsample: Optional[nn.Module] = None,
    ) -> None:
        super().__init__()
        width = out_channels
        self.conv1 = nn.Conv2d(
            in_channels, width, kernel_size=1, stride=1, bias=False)
        self.bn1 = nn.BatchNorm2d(width)
        self.conv2 = nn.Conv2d(width, width, kernel_size=3,
                               stride=stride, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(width)
        self.conv3 = nn.Conv2d(
            width, out_channels * self.expansion, kernel_size=1, stride=1, bias=False)
        self.bn3 = nn.BatchNorm2d(out_channels * self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        identity = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)
        out = self.conv3(out)
        out = self.bn3(out)
        if self.downsample is not None:
            identity = self.downsample(x)
        out += identity
        out = self.relu(out)
        return out


class ResNet(nn.Module):
    def __init__(
        self,
        block: Type[Union[BasicBlock, Bottleneck]],
        layers: List[int],
        num_classes: int = 100,
    ) -> None:
        super().__init__()
        self.in_channels = 64
        # Modified for CIFAR-100 (32x32 images)
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3,
                               stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * block.expansion, num_classes)

    def _make_layer(
        self,
        block: Type[Union[BasicBlock, Bottleneck]],
        out_channels: int,
        blocks: int,
        stride: int = 1,
    ) -> nn.Sequential:
        downsample = None
        if stride != 1 or self.in_channels != out_channels * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.in_channels, out_channels * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(out_channels * block.expansion),
            )

        layers = []
        layers.append(
            block(self.in_channels, out_channels, stride, downsample))
        self.in_channels = out_channels * block.expansion
        for _ in range(1, blocks):
            layers.append(block(self.in_channels, out_channels))

        return nn.Sequential(*layers)

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.fc(x)
        return x


def resnet18(num_classes: int = 100) -> ResNet:
    return ResNet(BasicBlock, [2, 2, 2, 2], num_classes=num_classes)


def resnet34(num_classes: int = 100) -> ResNet:
    return ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes)


def resnet50(num_classes: int = 100) -> ResNet:
    return ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes)