import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.nn import init as init
from torch.nn.modules.batchnorm import _BatchNorm
import matplotlib.pyplot as plt


class CvBlock(nn.Module):
	'''(Conv2d => BN => ReLU) x 2'''
	def __init__(self, in_ch, out_ch):
		super(CvBlock, self).__init__()
		self.convblock = nn.Sequential(
			nn.Conv2d(in_ch, out_ch, kernel_size=3, padding=1, bias=False),
			nn.BatchNorm2d(out_ch),
			nn.ReLU(inplace=True),
			nn.Conv2d(out_ch, out_ch, kernel_size=3, padding=1, bias=False),
			nn.BatchNorm2d(out_ch),
			nn.ReLU(inplace=True)
		)

	def forward(self, x):
		return self.convblock(x)


class InputCvBlock(nn.Module):
	'''(Conv with num_in_frames groups => BN => ReLU) + (Conv => BN => ReLU)'''
	def __init__(self, num_in_frames, out_ch):
		super(InputCvBlock, self).__init__()
		self.interm_ch = 30
		self.convblock = nn.Sequential(
			nn.Conv2d(num_in_frames*(3+1), num_in_frames*self.interm_ch, \
					  kernel_size=3, padding=1, groups=num_in_frames, bias=False),
			nn.BatchNorm2d(num_in_frames*self.interm_ch),
			nn.ReLU(inplace=True),
			nn.Conv2d(num_in_frames*self.interm_ch, out_ch, kernel_size=3, padding=1, bias=False),
			nn.BatchNorm2d(out_ch),
			nn.ReLU(inplace=True)
		)

	def forward(self, x):
		return self.convblock(x)


class InputCvBlock_1(nn.Module):
	'''(Conv with num_in_frames groups => BN => ReLU) + (Conv => BN => ReLU)'''
	def __init__(self, num_in_frames, out_ch):
		super(InputCvBlock_1, self).__init__()
		self.interm_ch = 30
		self.convblock = nn.Sequential(
			nn.Conv2d(num_in_frames*(3+1), num_in_frames*self.interm_ch, \
					  kernel_size=3, padding=1, groups=num_in_frames, bias=False),
			nn.BatchNorm2d(num_in_frames*self.interm_ch),
			nn.ReLU(inplace=True),
			nn.Conv2d(num_in_frames*self.interm_ch, out_ch, kernel_size=3, padding=1, bias=False),
			nn.BatchNorm2d(out_ch),
			nn.ReLU(inplace=True)
		)

		# self.NAF1 = NAFBlock(out_ch)
		# self.NAF2 = NAFBlock(out_ch)

	def forward(self, x):
		x = self.convblock(x)
		# x = self.NAF1(x)
		# return self.NAF2(x)
		return x


class DownBlock(nn.Module):
	'''Downscale + (Conv2d => BN => ReLU)*2'''
	def __init__(self, in_ch, out_ch):
		super(DownBlock, self).__init__()
		self.convblock = nn.Sequential(
			nn.Conv2d(in_ch, out_ch, kernel_size=3, padding=1, stride=2, bias=False),
			nn.BatchNorm2d(out_ch),
			nn.ReLU(inplace=True),
			CvBlock(out_ch, out_ch)
		)

	def forward(self, x):
		return self.convblock(x)
	

class DownBlock_1(nn.Module):
	'''Downscale + (Conv2d => BN => ReLU)*2'''
	def __init__(self, in_ch, out_ch):
		super(DownBlock_1, self).__init__()
		self.convblock = nn.Sequential(
			nn.Conv2d(in_ch, out_ch, kernel_size=3, padding=1, stride=2, bias=False),
			nn.BatchNorm2d(out_ch),
			nn.ReLU(inplace=True),
			CvBlock(out_ch, out_ch)
		)

		self.NAF1 = NAFBlock(in_ch)
		self.NAF2 = NAFBlock(in_ch)


	def forward(self, x):


		x = self.NAF1(x)
		x = self.NAF2(x)
		return self.convblock(x)
	

class UpBlock(nn.Module):
	'''(Conv2d => BN => ReLU)*2 + Upscale'''
	def __init__(self, in_ch, out_ch):
		super(UpBlock, self).__init__()
		self.convblock = nn.Sequential(
			CvBlock(in_ch, in_ch),
			nn.Conv2d(in_ch, out_ch*4, kernel_size=3, padding=1, bias=False),
			nn.PixelShuffle(2)
		)

	def forward(self, x):
		return self.convblock(x)
	

class UpBlock_1(nn.Module):
	'''(Conv2d => BN => ReLU)*2 + Upscale'''
	def __init__(self, in_ch, out_ch):
		super(UpBlock_1, self).__init__()
		self.convblock = nn.Sequential(
			CvBlock(in_ch, in_ch),
			nn.Conv2d(in_ch, out_ch*4, kernel_size=3, padding=1, bias=False),
			nn.PixelShuffle(2)
		)

		self.NAF1 = NAFBlock(in_ch)
		self.NAF2 = NAFBlock(in_ch)

	def forward(self, x):
		x = self.NAF1(x)
		x = self.NAF2(x)
		return self.convblock(x)
	

class OutputCvBlock(nn.Module):
	'''Conv2d => BN => ReLU => Conv2d'''
	def __init__(self, in_ch, out_ch):
		super(OutputCvBlock, self).__init__()
		self.convblock = nn.Sequential(
			nn.Conv2d(in_ch, in_ch, kernel_size=3, padding=1, bias=False),
			nn.BatchNorm2d(in_ch),
			nn.ReLU(inplace=True),
			nn.Conv2d(in_ch, out_ch, kernel_size=3, padding=1, bias=False)
		)

	def forward(self, x):
		return self.convblock(x)
	

class OutputCvBlock_1(nn.Module):
	'''Conv2d => BN => ReLU => Conv2d'''
	def __init__(self, in_ch, out_ch):
		super(OutputCvBlock_1, self).__init__()
		self.convblock = nn.Sequential(
			nn.Conv2d(in_ch, in_ch, kernel_size=3, padding=1, bias=False),
			nn.BatchNorm2d(in_ch),
			nn.ReLU(inplace=True),
			nn.Conv2d(in_ch, out_ch, kernel_size=3, padding=1, bias=False)
		)

		# self.NAF1 = NAFBlock(in_ch)
		# self.NAF2 = NAFBlock(in_ch)

	def forward(self, x):
		# x = self.NAF1(x)
		# x = self.NAF2(x)
		return self.convblock(x)


class SimpleGate(nn.Module):
    def forward(self, x):
        x1, x2 = x.chunk(2, dim=1)
        return x1 * x2


class LayerNormFunction(torch.autograd.Function):

    @staticmethod
    def forward(ctx, x, weight, bias, eps):
        ctx.eps = eps
        N, C, H, W = x.size()
        mu = x.mean(1, keepdim=True)
        var = (x - mu).pow(2).mean(1, keepdim=True)
        y = (x - mu) / (var + eps).sqrt()
        ctx.save_for_backward(y, var, weight)
        y = weight.view(1, C, 1, 1) * y + bias.view(1, C, 1, 1)
        return y

    @staticmethod
    def backward(ctx, grad_output):
        eps = ctx.eps

        N, C, H, W = grad_output.size()
        y, var, weight = ctx.saved_variables
        g = grad_output * weight.view(1, C, 1, 1)
        mean_g = g.mean(dim=1, keepdim=True)

        mean_gy = (g * y).mean(dim=1, keepdim=True)
        gx = 1. / torch.sqrt(var + eps) * (g - y * mean_gy - mean_g)
        return gx, (grad_output * y).sum(dim=3).sum(dim=2).sum(dim=0), grad_output.sum(dim=3).sum(dim=2).sum(
            dim=0), None


class LayerNorm2d(nn.Module):

    def __init__(self, channels, eps=1e-6):
        super(LayerNorm2d, self).__init__()
        self.register_parameter('weight', nn.Parameter(torch.ones(channels)))
        self.register_parameter('bias', nn.Parameter(torch.zeros(channels)))
        self.eps = eps

    def forward(self, x):
        return LayerNormFunction.apply(x, self.weight, self.bias, self.eps)


class NAFBlock(nn.Module):
    def __init__(self, c, DW_Expand=2, FFN_Expand=2, drop_out_rate=0.):
        super().__init__()
        dw_channel = c * DW_Expand
        self.conv1 = nn.Conv2d(in_channels=c, out_channels=dw_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
        self.conv2 = nn.Conv2d(in_channels=dw_channel, out_channels=dw_channel, kernel_size=3, padding=1, stride=1, groups=dw_channel,
                               bias=True)
        self.conv3 = nn.Conv2d(in_channels=dw_channel // 2, out_channels=c, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
        
        # Simplified Channel Attention
        self.sca = nn.Sequential(
            nn.AdaptiveAvgPool2d(1),
            nn.Conv2d(in_channels=dw_channel // 2, out_channels=dw_channel // 2, kernel_size=1, padding=0, stride=1,
                      groups=1, bias=True),
        )

        # SimpleGate
        self.sg = SimpleGate()

        ffn_channel = FFN_Expand * c
        self.conv4 = nn.Conv2d(in_channels=c, out_channels=ffn_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
        self.conv5 = nn.Conv2d(in_channels=ffn_channel // 2, out_channels=c, kernel_size=1, padding=0, stride=1, groups=1, bias=True)

        self.norm1 = LayerNorm2d(c)
        self.norm2 = LayerNorm2d(c)

        self.dropout1 = nn.Dropout(drop_out_rate) if drop_out_rate > 0. else nn.Identity()
        self.dropout2 = nn.Dropout(drop_out_rate) if drop_out_rate > 0. else nn.Identity()

        self.beta = nn.Parameter(torch.zeros((1, c, 1, 1)), requires_grad=True)
        self.gamma = nn.Parameter(torch.zeros((1, c, 1, 1)), requires_grad=True)

    def forward(self, inp):
        x = inp

        x = self.norm1(x)

        x = self.conv1(x)
        x = self.conv2(x)
        x = self.sg(x)
        x = x * self.sca(x)
        x = self.conv3(x)

        x = self.dropout1(x)

        y = inp + x * self.beta

        x = self.conv4(self.norm2(y))
        x = self.sg(x)
        x = self.conv5(x)

        x = self.dropout2(x)

        return y + x * self.gamma





















class DenBlock(nn.Module):
	""" Definition of the denosing block of FastDVDnet.
	Inputs of constructor:
		num_input_frames: int. number of input frames
	Inputs of forward():
		xn: input frames of dim [N, C, H, W], (C=3 RGB)
		noise_map: array with noise map of dim [N, 1, H, W]
	"""

	def __init__(self, num_input_frames=3):
		super(DenBlock, self).__init__()
		self.chs_lyr0 = 32
		self.chs_lyr1 = 64
		self.chs_lyr2 = 128

		self.inc = InputCvBlock(num_in_frames=num_input_frames, out_ch=self.chs_lyr0)
		self.downc0 = DownBlock(in_ch=self.chs_lyr0, out_ch=self.chs_lyr1)
		self.downc1 = DownBlock(in_ch=self.chs_lyr1, out_ch=self.chs_lyr2)
		self.upc2 = UpBlock(in_ch=self.chs_lyr2, out_ch=self.chs_lyr1)
		self.upc1 = UpBlock(in_ch=self.chs_lyr1, out_ch=self.chs_lyr0)
		self.outc = OutputCvBlock(in_ch=self.chs_lyr0, out_ch=3)


	def forward(self, in0, in1, in2, noise_map):
		'''Args:
			inX: Tensor, [N, C, H, W] in the [0., 1.] range
			noise_map: Tensor [N, 1, H, W] in the [0., 1.] range
		'''
		# Input convolution block
		x0 = self.inc(torch.cat((in0, noise_map, in1, noise_map, in2, noise_map), dim=1))
		# Downsampling
		x1 = self.downc0(x0)
		x2 = self.downc1(x1)
		# Upsampling
		x2 = self.upc2(x2)
		x1 = self.upc1(x1+x2)
		# Estimation
		x = self.outc(x0+x1)

		# Residual
		x = in1 - x

		return x


class DenBlock_1(nn.Module):
	""" Definition of the denosing block of FastDVDnet.
	Inputs of constructor:
		num_input_frames: int. number of input frames
	Inputs of forward():
		xn: input frames of dim [N, C, H, W], (C=3 RGB)
		noise_map: array with noise map of dim [N, 1, H, W]
	"""

	def __init__(self, num_input_frames=3):
		super(DenBlock_1, self).__init__()
		self.chs_lyr0 = 32
		self.chs_lyr1 = 64
		self.chs_lyr2 = 128

		self.inc = InputCvBlock_1(num_in_frames=num_input_frames, out_ch=self.chs_lyr0)
		self.downc0 = DownBlock_1(in_ch=self.chs_lyr0, out_ch=self.chs_lyr1)
		self.downc1 = DownBlock_1(in_ch=self.chs_lyr1, out_ch=self.chs_lyr2)
		self.upc2 = UpBlock_1(in_ch=self.chs_lyr2, out_ch=self.chs_lyr1)
		self.upc1 = UpBlock_1(in_ch=self.chs_lyr1, out_ch=self.chs_lyr0)
		self.outc = OutputCvBlock_1(in_ch=self.chs_lyr0, out_ch=3)
		

	def forward(self, in0, in1, in2, noise_map):
		'''Args:
			inX: Tensor, [N, C, H, W] in the [0., 1.] range
			noise_map: Tensor [N, 1, H, W] in the [0., 1.] range
		'''
		# Input convolution block
		x0 = self.inc(torch.cat((in0, noise_map, in1, noise_map, in2, noise_map), dim=1))
		# Downsampling
		x1 = self.downc0(x0)
		x2 = self.downc1(x1)
		# Upsampling
		x2 = self.upc2(x2)
		x1 = self.upc1(x1+x2)
		# Estimation
		x = self.outc(x0+x1)

		# Residual
		x = in1 - x

		return x