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


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, stride=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, stride=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * 4)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = F.relu(self.bn1(self.conv1(x)), inplace=True)
        out = F.relu(self.bn2(self.conv2(out)), inplace=True)
        out = self.bn3(self.conv3(out))

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = F.relu(out, inplace=True)

        return out


class ResNet(nn.Module):
    """ Resnet """
    def __init__(self, architecture):
        super(ResNet, self).__init__()
        assert architecture in ["resnet50", "resnet101"]
        self.inplanes = 64
        self.layers = [3, 4, {"resnet50": 6, "resnet101": 23}[architecture], 3]
        self.block = Bottleneck

        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64, eps=1e-5, momentum=0.01, affine=True)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2)

        self.layer1 = self.make_layer(self.block, 64, self.layers[0])
        self.layer2 = self.make_layer(self.block, 128, self.layers[1], stride=2)
        self.layer3 = self.make_layer(self.block, 256, self.layers[2], stride=2)

        self.layer4 = self.make_layer(
            self.block, 512, self.layers[3], stride=2)

    def forward(self, x):
        x = self.maxpool(self.relu(self.bn1(self.conv1(x))))
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        return x

    def stages(self):
        return [self.layer1, self.layer2, self.layer3, self.layer4]

    def make_layer(self, block, planes, blocks, stride=1):
        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),
                nn.BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))

        return nn.Sequential(*layers)