# -*- coding: utf-8 -*-
# @Author  : xuelun

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch import Tensor
from typing import Type, Callable, Union, List, Optional


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


def conv1x1(in_planes: int, out_planes: int, stride: int = 1) -> nn.Conv2d:
    """1x1 convolution"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)


class BasicBlock(nn.Module):
    expansion: int = 1

    def __init__(
        self,
        inplanes: int,
        planes: int,
        stride: int = 1,
        downsample: Optional[nn.Module] = None,
        groups: int = 1,
        base_width: int = 64,
        dilation: int = 1,
        norm_layer: Optional[Callable[..., nn.Module]] = None
    ) -> None:
        super(BasicBlock, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        if groups != 1 or base_width != 64:
            raise ValueError('BasicBlock only supports groups=1 and base_width=64')
        if dilation > 1:
            raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
        # Both self.conv1 and self.downsample layers downsample the input when stride != 1
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = norm_layer(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = norm_layer(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x: Tensor) -> Tensor:
        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):
    # Bottleneck in torchvision places the stride for downsampling at 3x3 convolution(self.conv2)
    # while original implementation places the stride at the first 1x1 convolution(self.conv1)
    # according to "Deep residual learning for image recognition"https://arxiv.org/abs/1512.03385.
    # This variant is also known as ResNet V1.5 and improves accuracy according to
    # https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch.

    expansion: int = 4

    def __init__(
        self,
        inplanes: int,
        planes: int,
        stride: int = 1,
        downsample: Optional[nn.Module] = None,
        groups: int = 1,
        base_width: int = 64,
        dilation: int = 1,
        norm_layer: Optional[Callable[..., nn.Module]] = None
    ) -> None:
        super(Bottleneck, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        width = int(planes * (base_width / 64.)) * groups
        # Both self.conv2 and self.downsample layers downsample the input when stride != 1
        self.conv1 = conv1x1(inplanes, width)
        self.bn1 = norm_layer(width)
        self.conv2 = conv3x3(width, width, stride, groups, dilation)
        self.bn2 = norm_layer(width)
        self.conv3 = conv1x1(width, planes * self.expansion)
        self.bn3 = norm_layer(planes * self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x: Tensor) -> Tensor:
        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 ResNet(nn.Module):

    def __init__(
        self,
        block: Type[Union[BasicBlock, Bottleneck]],
        layers: List[int],
        num_classes: int = 1000,
        zero_init_residual: bool = False,
        groups: int = 1,
        width_per_group: int = 64,
        replace_stride_with_dilation: Optional[List[bool]] = None,
        norm_layer: Optional[Callable[..., nn.Module]] = None
    ) -> None:
        super(ResNet, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        self._norm_layer = norm_layer

        self.inplanes = 64
        self.dilation = 1
        if replace_stride_with_dilation is None:
            # each element in the tuple indicates if we should replace
            # the 2x2 stride with a dilated convolution instead
            replace_stride_with_dilation = [False, False, False]
        if len(replace_stride_with_dilation) != 3:
            raise ValueError("replace_stride_with_dilation should be None "
                             "or a 3-element tuple, got {}".format(replace_stride_with_dilation))
        self.groups = groups
        self.base_width = width_per_group
        self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = norm_layer(self.inplanes)
        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,
                                       dilate=replace_stride_with_dilation[0])
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2,
                                       dilate=replace_stride_with_dilation[1])
        # self.layer4 = self._make_layer(block, 512, layers[3], stride=2,
        #                                dilate=replace_stride_with_dilation[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.GroupNorm)):
        #         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)  # type: ignore[arg-type]
        #         elif isinstance(m, BasicBlock):
        #             nn.init.constant_(m.bn2.weight, 0)  # type: ignore[arg-type]

    def _make_layer(self, block: Type[Union[BasicBlock, Bottleneck]], planes: int, blocks: int,
                    stride: int = 1, dilate: bool = False) -> nn.Sequential:
        norm_layer = self._norm_layer
        downsample = None
        previous_dilation = self.dilation
        if dilate:
            self.dilation *= stride
            stride = 1
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                conv1x1(self.inplanes, planes * block.expansion, stride),
                norm_layer(planes * block.expansion),
            )

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

        return nn.Sequential(*layers)

    def _forward_impl(self, x: Tensor) -> Tensor:
        # See note [TorchScript super()]
        # x = self.conv1(x)  # (2, 64, 320, 320)
        # x = self.bn1(x)  # (2, 64, 320, 320)
        # x1 = self.relu(x)  # (2, 64, 320, 320)
        # x2 = self.maxpool(x1)  # (2, 64, 160, 160)

        # x2 = self.layer1(x1)  # (2, 64, 160, 160)
        # x3 = self.layer2(x2)  # (2, 128, 80, 80)
        # x4 = self.layer3(x3)  # (2, 256, 40, 40)
        # x = self.layer4(x)  # (2, 512, 20, 20)

        # x = self.avgpool(x)  # (2, 512, 1, 1)
        # x = torch.flatten(x, 1)  # (2, 512)
        # x = self.fc(x)  # (2, 1000)

        x0 = self.relu(self.bn1(self.conv1(x)))
        x1 = self.layer1(x0)  # 1/2
        x2 = self.layer2(x1)  # 1/4
        x3 = self.layer3(x2)  # 1/8

        return x1, x2, x3

    def forward(self, x: Tensor) -> Tensor:
        return self._forward_impl(x)

    def load_state_dict(self, state_dict, *args, **kwargs):
        for k in list(state_dict.keys()):
            if k.startswith('layer4.'): state_dict.pop(k)
            if k.startswith('fc.'): state_dict.pop(k)
        return super().load_state_dict(state_dict, *args, **kwargs)


class ResNetFPN_8_2(nn.Module):
    """
    ResNet+FPN, output resolution are 1/8 and 1/2.
    Each block has 2 layers.
    """

    def __init__(self, config):
        super().__init__()
        # Config
        block = BasicBlock
        # initial_dim = config['initial_dim']
        block_dims = config['block_dims']

        # Class Variable
        # self.in_planes = initial_dim

        # Networks
        # self.conv1 = nn.Conv2d(1, initial_dim, kernel_size=7, stride=2, padding=3, bias=False)
        # self.bn1 = nn.BatchNorm2d(initial_dim)
        # self.relu = nn.ReLU(inplace=True)

        # self.layer1 = self._make_layer(block, block_dims[0], stride=1)  # 1/2
        # self.layer2 = self._make_layer(block, block_dims[1], stride=2)  # 1/4
        # self.layer3 = self._make_layer(block, block_dims[2], stride=2)  # 1/8

        self.encode = ResNet(Bottleneck, [3, 4, 6, 3])  # resnet50

        # 3. FPN upsample
        self.layer3_outconv = conv1x1(block_dims[5], block_dims[3])
        self.layer2_outconv = conv1x1(block_dims[4], block_dims[3])
        self.layer2_outconv2 = nn.Sequential(
            conv3x3(block_dims[3], block_dims[3]),
            nn.BatchNorm2d(block_dims[3]),
            nn.LeakyReLU(),
            conv3x3(block_dims[3], block_dims[2]),
        )
        self.layer1_outconv = conv1x1(block_dims[3], block_dims[2])
        self.layer1_outconv2 = nn.Sequential(
            conv3x3(block_dims[2], block_dims[2]),
            nn.BatchNorm2d(block_dims[2]),
            nn.LeakyReLU(),
            conv3x3(block_dims[2], block_dims[1]),
        )

        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.GroupNorm)):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

    def _make_layer(self, block, dim, stride=1):
        layer1 = block(self.in_planes, dim, stride=stride)
        layer2 = block(dim, dim, stride=1)
        layers = (layer1, layer2)

        self.in_planes = dim
        return nn.Sequential(*layers)

    def forward(self, x):
        # ResNet Backbone
        # x0 = self.relu(self.bn1(self.conv1(x)))
        # x1 = self.layer1(x0)  # 1/2
        # x2 = self.layer2(x1)  # 1/4
        # x3 = self.layer3(x2)  # 1/8

        # x1: (2, 64, 320, 320)
        # x2: (2, 128, 160, 160)
        # x3: (2, 256, 80, 80)
        x1, x2, x3 = self.encode(x)

        # FPN
        x3_out = self.layer3_outconv(x3)  # (2, 256, 80, 80)

        x3_out_2x = F.interpolate(x3_out, scale_factor=2., mode='bilinear', align_corners=True)  # (2, 256, 160, 160)
        x2_out = self.layer2_outconv(x2)  # (2, 256, 160, 160)
        x2_out = self.layer2_outconv2(x2_out+x3_out_2x)  # (2, 196, 160, 160)

        x2_out_2x = F.interpolate(x2_out, scale_factor=2., mode='bilinear', align_corners=True)  # (2, 196, 320, 320)
        x1_out = self.layer1_outconv(x1)  # (2, 196, 320, 320)
        x1_out = self.layer1_outconv2(x1_out+x2_out_2x)

        return [x3_out, x1_out]


if __name__ == '__main__':
    # Original form
    # config = dict(initial_dim=128, block_dims=[128, 196, 256])
    # model = ResNetFPN_8_2(config)
    # # output (list):
    # #   0:  (2, 256, 80, 80)
    # #   1:  (2, 128, 320, 320)
    # output = model(torch.randn(2, 1, 640, 640))

    # model = ResNet(BasicBlock, [2, 2, 2, 2])
    # # weights = torch.load('resnet18(5c106cde).ckpt', map_location='cpu')
    # # model.load_state_dict(weights)
    # output = model(torch.randn(2, 3, 640, 640))

    config = dict(initial_dim=128, block_dims=[64, 128, 196, 256])
    model = ResNetFPN_8_2(config)
    # output (list):
    #   0:  (2, 256, 80, 80)
    #   1:  (2, 128, 320, 320)
    output = model(torch.randn(2, 3, 640, 640))