import torch
import torch.nn as nn
import torch.nn.functional as F


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, in_planes, planes, stride=1, downsample=None, norm_layer=None):
        super().__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = norm_layer(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = norm_layer(planes)
        self.downsample = downsample

    def forward(self, x):
        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 ResNet(nn.Module):
    # ResNet-18 adapted for CIFAR (32x32): 3x3 stem, no maxpool.
    def __init__(self, block, layers, num_classes=100, width=64, norm_layer=None):
        super().__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d

        self.inplanes = width
        self.conv1 = nn.Conv2d(3, width, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn1 = norm_layer(width)
        self.relu = nn.ReLU(inplace=True)

        self.layer1 = self._make_layer(block, width, layers[0], stride=1, norm_layer=norm_layer)
        self.layer2 = self._make_layer(block, width*2, layers[1], stride=2, norm_layer=norm_layer)
        self.layer3 = self._make_layer(block, width*4, layers[2], stride=2, norm_layer=norm_layer)
        self.layer4 = self._make_layer(block, width*8, layers[3], stride=2, norm_layer=norm_layer)

        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Linear(width*8*block.expansion, num_classes)

        self._initialize_weights()

    def _make_layer(self, block, planes, blocks, stride, norm_layer):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False),
                norm_layer(planes * block.expansion),
            )
        layers = []
        layers.append(block(self.inplanes, planes, stride=stride, downsample=downsample, norm_layer=norm_layer))
        self.inplanes = planes * block.expansion
        for _ in range(1, blocks):
            layers.append(block(self.inplanes, planes, stride=1, norm_layer=norm_layer))
        return nn.Sequential(*layers)

    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1.0)
                nn.init.constant_(m.bias, 0.0)
            elif isinstance(m, nn.Linear):
                nn.init.kaiming_uniform_(m.weight, a=5**0.5)
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0.0)

    def forward(self, x):
        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_cifar(num_classes=100, width=64):
    # Standard ResNet-18 for CIFAR-100 with adjustable width (default 64).
    return ResNet(BasicBlock, [2, 2, 2, 2], num_classes=num_classes, width=width)