"""
Credit to https://github.com/XingangPan/IBN-Net.
"""
from __future__ import division, absolute_import
import math
import torch.nn as nn
import torch.utils.model_zoo as model_zoo

__all__ = ['resnet50_ibn_b']

model_urls = {
    '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):
    "3x3 convolution with padding"
    return nn.Conv2d(
        in_planes,
        out_planes,
        kernel_size=3,
        stride=stride,
        padding=1,
        bias=False
    )


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = 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:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None, IN=False):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=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 * self.expansion, kernel_size=1, bias=False
        )
        self.bn3 = nn.BatchNorm2d(planes * self.expansion)
        self.IN = None
        if IN:
            self.IN = nn.InstanceNorm2d(planes * 4, affine=True)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = 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:
            residual = self.downsample(x)

        out += residual
        if self.IN is not None:
            out = self.IN(out)
        out = self.relu(out)

        return out


class ResNet(nn.Module):
    """Residual network + IBN layer.
    
    Reference:
        - He et al. Deep Residual Learning for Image Recognition. CVPR 2016.
        - Pan et al. Two at Once: Enhancing Learning and Generalization
          Capacities via IBN-Net. ECCV 2018.
    """

    def __init__(
        self,
        block,
        layers,
        num_classes=1000,
        loss='softmax',
        fc_dims=None,
        dropout_p=None,
        **kwargs
    ):
        scale = 64
        self.inplanes = scale
        super(ResNet, self).__init__()
        self.loss = loss
        self.feature_dim = scale * 8 * block.expansion

        self.conv1 = nn.Conv2d(
            3, scale, kernel_size=7, stride=2, padding=3, bias=False
        )
        self.bn1 = nn.InstanceNorm2d(scale, affine=True)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(
            block, scale, layers[0], stride=1, IN=True
        )
        self.layer2 = self._make_layer(
            block, scale * 2, layers[1], stride=2, IN=True
        )
        self.layer3 = self._make_layer(block, scale * 4, layers[2], stride=2)
        self.layer4 = self._make_layer(block, scale * 8, layers[3], stride=2)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = self._construct_fc_layer(
            fc_dims, scale * 8 * block.expansion, dropout_p
        )
        self.classifier = nn.Linear(self.feature_dim, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
                m.weight.data.normal_(0, math.sqrt(2. / n))
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
            elif isinstance(m, nn.InstanceNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()

    def _make_layer(self, block, planes, blocks, stride=1, IN=False):
        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 - 1):
            layers.append(block(self.inplanes, planes))
        layers.append(block(self.inplanes, planes, IN=IN))

        return nn.Sequential(*layers)

    def _construct_fc_layer(self, fc_dims, input_dim, dropout_p=None):
        """Constructs fully connected layer

        Args:
            fc_dims (list or tuple): dimensions of fc layers, if None, no fc layers are constructed
            input_dim (int): input dimension
            dropout_p (float): dropout probability, if None, dropout is unused
        """
        if fc_dims is None:
            self.feature_dim = input_dim
            return None

        assert isinstance(
            fc_dims, (list, tuple)
        ), 'fc_dims must be either list or tuple, but got {}'.format(
            type(fc_dims)
        )

        layers = []
        for dim in fc_dims:
            layers.append(nn.Linear(input_dim, dim))
            layers.append(nn.BatchNorm1d(dim))
            layers.append(nn.ReLU(inplace=True))
            if dropout_p is not None:
                layers.append(nn.Dropout(p=dropout_p))
            input_dim = dim

        self.feature_dim = fc_dims[-1]

        return nn.Sequential(*layers)

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

    def forward(self, x):
        f = self.featuremaps(x)
        v = self.avgpool(f)
        v = v.view(v.size(0), -1)
        if self.fc is not None:
            v = self.fc(v)
        if not self.training:
            return v
        y = self.classifier(v)
        if self.loss == 'softmax':
            return y
        elif self.loss == 'triplet':
            return y, v
        else:
            raise KeyError("Unsupported loss: {}".format(self.loss))


def init_pretrained_weights(model, model_url):
    """Initializes model with pretrained weights.
    
    Layers that don't match with pretrained layers in name or size are kept unchanged.
    """
    pretrain_dict = model_zoo.load_url(model_url)
    model_dict = model.state_dict()
    pretrain_dict = {
        k: v
        for k, v in pretrain_dict.items()
        if k in model_dict and model_dict[k].size() == v.size()
    }
    model_dict.update(pretrain_dict)
    model.load_state_dict(model_dict)


def resnet50_ibn_b(num_classes, loss='softmax', pretrained=False, **kwargs):
    model = ResNet(
        Bottleneck, [3, 4, 6, 3], num_classes=num_classes, loss=loss, **kwargs
    )
    if pretrained:
        init_pretrained_weights(model, model_urls['resnet50'])
    return model