from typing import Union, Tuple

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

from .utils.logger import DummyLogger


class LayerInfo():
    def __init__(self):
        self.memory = 0.0
        self.ops = 0.0
        self.output = 0.0


class Layer(nn.Module):
    # Default layer arguments
    ACTIVATION = F.leaky_relu

    BATCH_NORM = True
    BATCH_NORM_TRAINING = True
    BATCH_NORM_MOMENTUM = 0.01

    IS_TRAINING = False
    METRICS = False
    VERBOSE = 0
    LOGGER = DummyLogger()

    def __init__(self, activation, batch_norm):
        super().__init__()
        self.name = 'Layer'
        self.info = LayerInfo()

        # Preload default
        if activation == 0:
            activation = Layer.ACTIVATION
        if isinstance(activation, type):
            self.activation = activation()
        else:
            self.activation = activation
        self.batch_norm = Layer.BATCH_NORM if batch_norm is None else 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.batch_norm is not None:
            output = self.batch_norm(output)
        return output


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

        self.conv = nn.Conv1d(in_channels, out_channels, kernel_size, stride=stride,
                              bias=not self.batch_norm, **kwargs)
        self.batch_norm = nn.BatchNorm1d(
            out_channels,
            momentum=Layer.BATCH_NORM_MOMENTUM,
            track_running_stats=Layer.BATCH_NORM_TRAINING) if self.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, batch_norm=None, **kwargs):
        super().__init__(activation, batch_norm)

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

        self.conv = nn.Conv3d(in_channels, out_channels, kernel_size, stride=stride,
                              bias=not self.batch_norm, **kwargs)
        self.batch_norm = nn.BatchNorm3d(
            out_channels,
            momentum=Layer.BATCH_NORM_MOMENTUM,
            track_running_stats=Layer.BATCH_NORM_TRAINING) if self.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, batch_norm=None, **kwargs):
        super().__init__(activation, batch_norm)

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

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