# taken from torchvision.models.convnext

from functools import partial
from typing import Any, Callable, List, Optional, Sequence

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

from torchvision.ops.misc import Conv2dNormActivation, Permute
# from torchvision.ops.misc import ConvNormActivation as Conv2dNormActivation
# from torchvision.ops import Permute
from torchvision.ops.stochastic_depth import StochasticDepth
from utils.convnext_utils import CNBlockConfig


__all__ = [
    "ConvNeXt",
    "ConvNeXt_Tiny_Weights",
    "ConvNeXt_Small_Weights",
    "ConvNeXt_Base_Weights",
    "ConvNeXt_Large_Weights",
    "convnext_tiny",
    "convnext_small",
    "convnext_base",
    "convnext_large",
]


class LayerNorm2d(nn.LayerNorm):
    def forward(self, x: Tensor) -> Tensor:
        x = x.permute(0, 2, 3, 1)
        x = F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
        x = x.permute(0, 3, 1, 2)
        return x


class CNBlock(nn.Module):
    def __init__(
        self,
        dim,
        layer_scale: float = 1e-6,
        stochastic_depth_prob: float = 0.0,
        kernel_size: int = 7,
        norm_layer: Optional[Callable[..., nn.Module]] = None,
    ) -> None:
        super().__init__()
        if norm_layer is None:
            norm_layer = partial(nn.LayerNorm, eps=1e-6)

        self.block = nn.Sequential(
            nn.Conv2d(dim, dim, kernel_size=kernel_size, padding='same', groups=dim, bias=True),
            Permute([0, 2, 3, 1]),
            norm_layer(dim),
            nn.Linear(in_features=dim, out_features=4 * dim, bias=True),
            nn.GELU(),
            nn.Linear(in_features=4 * dim, out_features=dim, bias=True),
            Permute([0, 3, 1, 2]),
        )
        self.layer_scale = nn.Parameter(torch.ones(dim, 1, 1) * layer_scale)
        self.stochastic_depth = StochasticDepth(stochastic_depth_prob, "row")

    def forward(self, input: Tensor) -> Tensor:
        result = self.layer_scale * self.block(input)
        result = self.stochastic_depth(result)
        result += input
        return result


class ConvNeXtBase(nn.Module):
    def __init__(
        self,
        block_setting: List[CNBlockConfig],
        stochastic_depth_prob: float = 0.0,
        layer_scale: float = 1e-6,
        block: Optional[Callable[..., nn.Module]] = None,
        norm_layer: Optional[Callable[..., nn.Module]] = None,
        device: str = 'cuda',
        kernel_size: int = 7,
    ) -> None:
        super().__init__()

        if not block_setting:
            raise ValueError("The block_setting should not be empty")
        elif not (isinstance(block_setting, Sequence) and all([isinstance(s, CNBlockConfig) for s in block_setting])):
            raise TypeError("The block_setting should be List[CNBlockConfig]")

        if block is None:
            block = CNBlock

        if norm_layer is None:
            norm_layer = partial(LayerNorm2d, eps=1e-6)

        # self.permute_cf = Permute([0, 3, 1, 2])
        # self.permute_cl = Permute([0, 2, 3, 1])

        self.stages: List[nn.Module] = []
        self.downsamples: List[nn.Module] = []

        # Stem
        firstconv_output_channels = block_setting[0].input_channels
        self.stem = Conv2dNormActivation(
                3,
                firstconv_output_channels,
                kernel_size=4,
                stride=4,
                padding=0,
                norm_layer=norm_layer,
                activation_layer=None,
                bias=True,
            ).to(device)
        

        total_stage_blocks = sum(cnf.num_layers for cnf in block_setting)
        stage_block_id = 0
        for cnf in block_setting:
            # Bottlenecks
            stage: List[nn.Module] = []
            for _ in range(cnf.num_layers):
                # adjust stochastic depth probability based on the depth of the stage block
                sd_prob = stochastic_depth_prob * stage_block_id / (total_stage_blocks - 1.0)
                stage.append(block(cnf.input_channels, layer_scale, sd_prob, kernel_size))
                stage_block_id += 1
            self.stages.append(nn.Sequential(*stage).to(device))
            if cnf.out_channels is not None:
                # Downsampling
                self.downsamples.append(
                    nn.Sequential(
                        norm_layer(cnf.input_channels),
                        nn.Conv2d(cnf.input_channels, cnf.out_channels, kernel_size=2, stride=2),
                    ).to(device)
                )

        self.act = nn.Tanh()

        for m in self.modules():
            if isinstance(m, (nn.Conv2d, nn.Linear)):
                nn.init.trunc_normal_(m.weight, std=0.02)
                if m.bias is not None:
                    nn.init.zeros_(m.bias)

    def _forward_impl(self, x: Tensor) -> Tensor:
        # x = self.permute_cf(x)
        x = self.stem(x)
        # features: List[Tensor] = []
        for i in range(len(self.stages) - 1):
            x = self.stages[i](x)
            # features.append(x)
            x = self.downsamples[i](x)
        x = self.stages[-1](x)
        x = self.act(x)

        # x = self.permute_cl(x)
        return x

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



class ConvNeXtReverseBase2(nn.Module):
    def __init__(
        self,
        block_setting: List[CNBlockConfig],
        stochastic_depth_prob: float = 0.0,
        layer_scale: float = 1e-6,
        block: Optional[Callable[..., nn.Module]] = None,
        norm_layer: Optional[Callable[..., nn.Module]] = None,
        device: str = 'cuda',
        use_skip: bool = False,
        is_label: bool = False,
        nr_of_labels: Optional[int] = None,
        kernel_size: int = 7,
    ) -> None:
        super().__init__()

        self.use_skip = use_skip

        if not block_setting:
            raise ValueError("The block_setting should not be empty")
        elif not (isinstance(block_setting, Sequence) and all([isinstance(s, CNBlockConfig) for s in block_setting])):
            raise TypeError("The block_setting should be List[CNBlockConfig]")

        if block is None:
            block = CNBlock

        if norm_layer is None:
            norm_layer = partial(LayerNorm2d, eps=1e-6)

        # self.permute_cf = Permute([0, 3, 1, 2])
        # self.permute_cl = Permute([0, 2, 3, 1])

        # Stem
        # firstconv_output_channels = block_setting[0].input_channels
        # self.first = nn.Sequential(
        #             nn.ConvTranspose2d(
        #                 firstconv_output_channels,
        #                 firstconv_output_channels,
        #                 kernel_size=2,
        #                 stride=2,
        #                 padding=0,
        #                 ),
        #             norm_layer(firstconv_output_channels),
        #         ).to(device)
        self.first = nn.Sequential(
                        nn.ConvTranspose2d(block_setting[0].input_channels, block_setting[0].out_channels, kernel_size=2, stride=2),
                        norm_layer(block_setting[0].out_channels),
                    ).to(device)


        total_stage_blocks = sum(cnf.num_layers for cnf in block_setting)
        stage_block_id = 0
        self.stages: List[nn.Module] = []
        self.upsamples: List[nn.Module] = []
        for cnf in block_setting[1:]:
            if cnf.input_channels is not None:
                # Bottlenecks
                stage: List[nn.Module] = []
                for _ in range(cnf.num_layers):
                    # adjust stochastic depth probability based on the depth of the stage block
                    sd_prob = stochastic_depth_prob * stage_block_id / (total_stage_blocks - 1.0)
                    stage.append(block(cnf.input_channels, layer_scale, sd_prob, kernel_size))
                    stage_block_id += 1
                self.stages.append(nn.Sequential(*stage).to(device))
            else:
                self.stages.append(nn.Identity().to(device))

            if cnf.out_channels is not None:
                # Upsampling
                self.upsamples.append(
                    nn.Sequential(
                        norm_layer(cnf.input_channels),
                        nn.ConvTranspose2d(cnf.input_channels, cnf.out_channels, kernel_size=2, stride=2),
                    ).to(device)
                )

        self.last = nn.Conv2d(
                    block_setting[-1].input_channels,
                    3 if not is_label else nr_of_labels,
                    kernel_size=3,
                    padding='same',
                    ).to(device)
        self.activation = nn.Tanh() if not is_label else nn.Softmax(dim=1)

        # self.last = nn.Sequential(
        #                 Permute([0, 2, 3, 1]),
        #                 nn.Linear(in_features=block_setting[-1].input_channels, out_features=1, bias=True),
        #                 Permute([0, 3, 1, 2]),
        #             ).to(device)


        for m in self.modules():
            if isinstance(m, (nn.Conv2d, nn.Linear)):
                nn.init.trunc_normal_(m.weight, std=0.02)
                if m.bias is not None:
                    nn.init.zeros_(m.bias)


    def _forward_impl(self, x) -> Tensor:
        # input, features = x
        # x = self.permute_cf(x)

        x = self.first(x)
        for i in range(len(self.stages)):
            # if self.use_skip:
            #     x = self.stages[i](torch.concat((x, features[2-i]), dim=1))
            # else:
            x = self.stages[i](x)
            x = self.upsamples[i](x)
        
        # x = self.stages[-2](x)
        # x = self.upsamples[-1](x)

        # x = self.stages[-1](x)
        x = self.last(x)
        x = self.activation(x)
        # x = self.permute_cl(x)
        
        return x

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


class ConvNeXtReverseBase(nn.Module):
    def __init__(
        self,
        block_setting: List[CNBlockConfig],
        stochastic_depth_prob: float = 0.0,
        layer_scale: float = 1e-6,
        block: Optional[Callable[..., nn.Module]] = None,
        norm_layer: Optional[Callable[..., nn.Module]] = None
    ) -> None:
        super().__init__()

        if not block_setting:
            raise ValueError("The block_setting should not be empty")
        elif not (isinstance(block_setting, Sequence) and all([isinstance(s, CNBlockConfig) for s in block_setting])):
            raise TypeError("The block_setting should be List[CNBlockConfig]")

        if block is None:
            block = CNBlock

        if norm_layer is None:
            norm_layer = partial(LayerNorm2d, eps=1e-6)

        layers: List[nn.Module] = []


        # add bottleneck which will be executed at the end, to process after the final larger upsampling



        # Stem
        firstconv_output_channels = block_setting[0].input_channels

        layers.append(
            nn.Sequential(
                nn.Conv2d(16, 1, kernel_size=7, padding=3, bias=True),

            )
        )

        stage: List[nn.Module] = []
        for _ in range(3):
            stage.append(block(16, layer_scale, 0.0))
        layers.append(nn.Sequential(*stage))
        
        layers.append(
            # Convtr NormActivation(
            #     firstconv_output_channels,
            #     3,
            #     kernel_size=4,
            #     stride=4,
            #     padding=0,
            #     norm_layer=None,
            #     activation_layer=None,
            #     bias=True,
            # )
            nn.Sequential(
                nn.ConvTranspose2d(
                    firstconv_output_channels,
                    16,
                    kernel_size=4,
                    stride=4,
                    padding=0,
                    ),
            )
        )

        total_stage_blocks = sum(cnf.num_layers for cnf in block_setting)
        stage_block_id = 0
        for cnf in block_setting:
            # Bottlenecks
            stage: List[nn.Module] = []
            for _ in range(cnf.num_layers):
                # adjust stochastic depth probability based on the depth of the stage block
                sd_prob = stochastic_depth_prob * stage_block_id / (total_stage_blocks - 1.0)
                stage.append(block(cnf.input_channels, layer_scale, sd_prob))
                stage_block_id += 1
            layers.append(nn.Sequential(*stage))
            if cnf.out_channels is not None:
                # Upsampling
                layers.append(
                    nn.Sequential(
                        norm_layer(cnf.out_channels),
                        nn.ConvTranspose2d(cnf.out_channels, cnf.input_channels, kernel_size=2, stride=2),
                    )
                )

        self.features = nn.Sequential(*reversed(layers))

        for m in self.modules():
            if isinstance(m, (nn.Conv2d, nn.Linear)):
                nn.init.trunc_normal_(m.weight, std=0.02)
                if m.bias is not None:
                    nn.init.zeros_(m.bias)

    def _forward_impl(self, x: Tensor) -> Tensor:
        x = self.features(x)
        # x = torch.tanh(x)
        return x

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


def _convnext(
    block_setting: List[CNBlockConfig],
    stochastic_depth_prob: float,
    reversed: bool,
    is_label: bool,
    nr_of_labels: Optional[int],
    kernel_size: int,
    device='cuda',
    **kwargs: Any,
) -> ConvNeXtBase:

    if reversed:
        model = ConvNeXtReverseBase2(block_setting, stochastic_depth_prob=stochastic_depth_prob, is_label=is_label, nr_of_labels=nr_of_labels, kernel_size=kernel_size, device=device, **kwargs)
    else:
        model = ConvNeXtBase(block_setting, stochastic_depth_prob=stochastic_depth_prob, kernel_size=kernel_size, device=device, **kwargs)


    return model


class ConvNeXt(nn.Module):
    def __init__(self, block_setting, stochastic_depth_prob=0.0, reversed=False, is_label=False, nr_of_labels=None, kernel_size=7, device='cuda', **kwargs) -> None:
        super().__init__()

        self.model = _convnext(block_setting, stochastic_depth_prob, reversed, is_label, nr_of_labels, kernel_size, device=device, **kwargs)

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


if __name__ == '__main__':
    model = ConvNeXt().to('cuda')
    test = model(torch.zeros((4, 3, 512, 256)).to('cuda'))

    pass