r""" ResNet-101 backbone network """

import torch.utils.model_zoo as model_zoo
import torch.nn as nn
import torch


__all__ = ['Backbone', 'resnet101']


model_urls = {
    'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
    'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
    'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
    'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
    'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
}


def conv3x3(in_planes, out_planes, stride=1):
    r""" 3x3 convolution with padding """
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=1, groups=2, bias=False)


def conv1x1(in_planes, out_planes, stride=1):
    r""" 1x1 convolution """
    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, groups=2, bias=False)


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = conv1x1(inplanes, planes)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = conv3x3(planes, planes, stride)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = conv1x1(planes, planes * self.expansion)
        self.bn3 = nn.BatchNorm2d(planes * self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    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)
        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 Backbone(nn.Module):
    def __init__(self, block, layers, zero_init_residual=False):
        super(Backbone, self).__init__()

        self.inplanes = 128
        self.conv1 = nn.Conv2d(6, 128, kernel_size=7, stride=2, padding=3, groups=2,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(128)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 128, layers[0])
        self.layer2 = self._make_layer(block, 256, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 512, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 1024, layers[3], stride=2)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512 * block.expansion, 1000)

        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)
                nn.init.constant_(m.bias, 0)

        # Zero-initialize the last BN in each residual branch,
        # so that the residual branch starts with zeros, and each residual block behaves like an identity.
        # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
        if zero_init_residual:
            for m in self.modules():
                if isinstance(m, Bottleneck):
                    nn.init.constant_(m.bn3.weight, 0)

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                conv1x1(self.inplanes, planes * block.expansion, stride),
                nn.BatchNorm2d(planes * block.expansion),
            )

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

        return nn.Sequential(*layers)


def resnet101(pretrained=False, **kwargs):
    """Constructs a ResNet-101 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = Backbone(Bottleneck, [3, 4, 23, 3], **kwargs)
    if pretrained:
        weights = model_zoo.load_url(model_urls['resnet101'])

        for key in weights:
            if key.split('.')[0] == 'fc':
                weights[key] = weights[key].clone()
                continue
            weights[key] = torch.cat([weights[key].clone(), weights[key].clone()], dim=0)

        model.load_state_dict(weights)
    return model