"""
From https://github.com/joe-siyuan-qiao/pytorch-classification
@article{weightstandardization,
  author    = {Siyuan Qiao and Huiyu Wang and Chenxi Liu and Wei Shen and Alan Yuille},
  title     = {Weight Standardization},
  journal   = {arXiv preprint arXiv:1903.10520},
  year      = {2019},
}
"""

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


class Conv2d(nn.Conv2d):
    def __init__(self, in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True):
        super(Conv2d, self).__init__(in_channels, out_channels, kernel_size, stride, padding, dilation, groups, bias)

    def forward(self, x):
        # return super(Conv2d, self).forward(x)
        weight = self.weight
        weight_mean = weight.mean(dim=1, keepdim=True).mean(dim=2, keepdim=True).mean(dim=3, keepdim=True)
        weight = weight - weight_mean
        std = weight.view(weight.size(0), -1).std(dim=1).view(-1, 1, 1, 1) + 1e-5
        weight = weight / std.expand_as(weight)
        return F.conv2d(x, weight, self.bias, self.stride, self.padding, self.dilation, self.groups)


class Linear(nn.Linear):
    def forward(self, x):
        weight = self.weight
        weight_mean = weight.mean(dim=1, keepdim=True)
        weight = weight - weight_mean
        std = weight.std(dim=1, keepdim=True) + 1e-5
        weight = weight / std.expand_as(weight)
        return F.linear(x, weight, self.bias)


def BatchNorm2d(num_features):
    return nn.GroupNorm(num_channels=num_features, num_groups=32)


__all__ = ["ws_resnet18", "ws_resnet34", "ws_resnet50", "ws_resnet101", "ws_resnet152"]


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


def conv1x1(in_planes, out_planes, stride=1):
    """1x1 convolution"""
    return Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, 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 = BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = BatchNorm2d(planes)
        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)

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

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

        return out


class Bottleneck(nn.Module):
    expansion = 4 # so that it can run

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

    def forward(self, x):
        identity = x
        # print(f"Input shape: {x.shape}")

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        # print(f"After conv1: {out.shape}")

        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)
        # print(f"After conv2: {out.shape}")

        out = self.conv3(out)
        out = self.bn3(out)
        # print(f"After conv3: {out.shape}")

        if self.downsample is not None:
            identity = self.downsample(x)
            # print(f"After downsample: {identity.shape}")
        # assert out.shape == identity.shape, f"Shape mismatch: out {out.shape}, identity {identity.shape}"

        out += identity
        out = self.relu(out)
        # print(f"Output shape: {out.shape}")

        return out


chan_size = 2
class ResNet(nn.Module):
    def __init__(self, block, layers, num_classes=1000, zero_init_residual=False):
        super(ResNet, self).__init__()
        self.inplanes = 64
        self.conv1 = Conv2d(in_channels=chan_size, out_channels=64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        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)

        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)
                elif isinstance(m, BasicBlock):
                    nn.init.constant_(m.bn2.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),
                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 forward(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)

        x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)

        return x


def ws_resnet18(pretrained=False, **kwargs):
    """Constructs a ResNet-18 model.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
    return model


def ws_resnet34(pretrained=False, **kwargs):
    """Constructs a ResNet-34 model.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
    return model


def ws_resnet50(pretrained=False, **kwargs):
    """Constructs a ResNet-50 model.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
    return model


def ws_resnet101(pretrained=False, **kwargs):
    """Constructs a ResNet-101 model.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
    return model


def ws_resnet152(pretrained=False, **kwargs):
    """Constructs a ResNet-152 model.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
    return model