from typing import Union, Tuple

import torch
import torch.nn as nn

from .utils.logger import DummyLogger


class Layer(nn.Module):
    # Default layer arguments
    ACTIVATION = torch.nn.LeakyReLU
    ACTIVATION_KWARGS = {"negative_slope": 0.1}

    USE_BATCH_NORM = True
    BATCH_NORM_TRAINING = True
    BATCH_NORM_MOMENTUM = 0.01

    IS_TRAINING = False
    METRICS = False
    LOGGER = DummyLogger()

    def __init__(self, activation, use_batch_norm):
        super().__init__()
        # Preload default
        self.batch_norm: torch.nn._BatchNorm = None
        self.activation = Layer.ACTIVATION if activation == 0 else activation
        self.use_batch_norm = Layer.USE_BATCH_NORM if use_batch_norm is None else use_batch_norm

    def forward(self, input_data: torch.Tensor) -> torch.Tensor:
        output = input_data
        if self.activation is not None:
            output = self.activation(output)
        if self.use_batch_norm:
            # It is assumed here that if using batch norm, then self.batch_norm has been instanciated.
            output = self.batch_norm(output)
        return output


class Linear(Layer):
    def __init__(self, in_channels: int, out_channels: int, activation=0, use_batch_norm: bool = None, **kwargs):
        super().__init__(activation, use_batch_norm)

        self.fc = nn.Linear(in_channels, out_channels, **kwargs)
        self.batch_norm = nn.BatchNorm1d(
            out_channels,
            momentum=Layer.BATCH_NORM_MOMENTUM,
            track_running_stats=Layer.BATCH_NORM_TRAINING) if self.use_batch_norm else None

    def forward(self, input_data: torch.Tensor) -> torch.Tensor:
        return super().forward(self.fc(input_data))


class Conv1d(Layer):
    def __init__(self, in_channels: int, out_channels: int, kernel_size: int = 3,
                 stride: Union[int, Tuple[int, int]] = 1, activation=0, use_batch_norm: bool = None, **kwargs):
        super().__init__(activation, use_batch_norm)

        self.conv = nn.Conv1d(in_channels, out_channels, kernel_size, stride=stride,
                              bias=not Layer.USE_BATCH_NORM, **kwargs)
        self.batch_norm = nn.BatchNorm1d(
            out_channels,
            momentum=Layer.BATCH_NORM_MOMENTUM,
            track_running_stats=Layer.BATCH_NORM_TRAINING) if self.use_batch_norm else None

    def forward(self, input_data: torch.Tensor) -> torch.Tensor:
        return super().forward(self.conv(input_data))


class Conv2d(Layer):
    def __init__(self, in_channels: int, out_channels: int, kernel_size: int = 3,
                 stride: Union[int, Tuple[int, int]] = 1, activation=0, use_batch_norm: bool = None, **kwargs):
        super().__init__(activation, use_batch_norm)

        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride=stride,
                              bias=not Layer.USE_BATCH_NORM, **kwargs)
        self.batch_norm = nn.BatchNorm2d(
            out_channels,
            momentum=Layer.BATCH_NORM_MOMENTUM,
            track_running_stats=not Layer.BATCH_NORM_TRAINING if Layer.USE_BATCH_NORM else None

    def forward(self, input_data: torch.Tensor) -> torch.Tensor:
        return super().forward(self.conv(input_data))


class Conv3d(Layer):
    def __init__(self, in_channels: int, out_channels: int, kernel_size: int = 3,
                 stride: Union[int, Tuple[int, int]] = 1, activation=0, use_batch_norm: bool = None, **kwargs):
        super().__init__(activation, use_batch_norm)

        self.conv = nn.Conv3d(in_channels, out_channels, kernel_size, stride=stride,
                              bias=not Layer.USE_BATCH_NORM, **kwargs)
        self.batch_norm = nn.BatchNorm3d(
            out_channels,
            momentum=Layer.BATCH_NORM_MOMENTUM,
            track_running_stats=Layer.BATCH_NORM_TRAINING) if self.use_batch_norm else None

    def forward(self, input_data: torch.Tensor) -> torch.Tensor:
        return super().forward(self.conv(input_data))


class Deconv2d(Layer):
    def __init__(self, in_channels: int, out_channels: int, kernel_size: int = 3,
                 stride: Union[int, Tuple[int, int]] = 1, activation=0, use_batch_norm: bool = None, **kwargs):
        super().__init__(activation, use_batch_norm)

        self.deconv = nn.ConvTranspose2d(
            in_channels, out_channels, kernel_size, stride=stride,
            bias=not Layer.USE_BATCH_NORM, **kwargs)
        self.batch_norm = nn.BatchNorm2d(
            out_channels,
            momentum=Layer.BATCH_NORM_MOMENTUM,
            track_running_stats=not Layer.BATCH_NORM_TRAINING if Layer.USE_BATCH_NORM else None

    def forward(self, input_data: torch.Tensor) -> torch.Tensor:
        return super().forward(self.deconv(input_data))