import math
import torch
from torch import nn
from torch.nn import functional as F

import torchaudio.transforms as T

from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
from torch.nn.utils import weight_norm, remove_weight_norm

import commons
from commons import init_weights, get_padding
from transforms import piecewise_rational_quadratic_transform
from torch.cuda.amp import autocast
from timm.models.vision_transformer import Attention
from itertools import repeat
import collections.abc
LRELU_SLOPE = 0.1

class LayerNorm(nn.Module):
    def __init__(self, channels, eps=1e-5):
        super().__init__()
        self.channels = channels
        self.eps = eps

        self.gamma = nn.Parameter(torch.ones(channels))
        self.beta = nn.Parameter(torch.zeros(channels))

    def forward(self, x):
        x = x.transpose(1, -1)
        x = F.layer_norm(x, (self.channels,), self.gamma, self.beta, self.eps)
        return x.transpose(1, -1)


class ConvReluNorm(nn.Module):
    def __init__(self, in_channels, hidden_channels, out_channels, kernel_size, n_layers, p_dropout):
        super().__init__()
        self.in_channels = in_channels
        self.hidden_channels = hidden_channels
        self.out_channels = out_channels
        self.kernel_size = kernel_size
        self.n_layers = n_layers
        self.p_dropout = p_dropout
        assert n_layers > 1, "Number of layers should be larger than 0."

        self.conv_layers = nn.ModuleList()
        self.norm_layers = nn.ModuleList()
        self.conv_layers.append(nn.Conv1d(in_channels, hidden_channels, kernel_size, padding=kernel_size // 2))
        self.norm_layers.append(LayerNorm(hidden_channels))
        self.relu_drop = nn.Sequential(
            nn.ReLU(),
            nn.Dropout(p_dropout))
        for _ in range(n_layers - 1):
            self.conv_layers.append(nn.Conv1d(hidden_channels, hidden_channels, kernel_size, padding=kernel_size // 2))
            self.norm_layers.append(LayerNorm(hidden_channels))
        self.proj = nn.Conv1d(hidden_channels, out_channels, 1)
        self.proj.weight.data.zero_()
        self.proj.bias.data.zero_()

    def forward(self, x, x_mask):
        x_org = x
        for i in range(self.n_layers):
            x = self.conv_layers[i](x * x_mask)
            x = self.norm_layers[i](x)
            x = self.relu_drop(x)
        x = x_org + self.proj(x)
        return x * x_mask


class DDSConv(nn.Module):
    """
    Dialted and Depth-Separable Convolution
    """

    def __init__(self, channels, kernel_size, n_layers, p_dropout=0.):
        super().__init__()
        self.channels = channels
        self.kernel_size = kernel_size
        self.n_layers = n_layers
        self.p_dropout = p_dropout

        self.drop = nn.Dropout(p_dropout)
        self.convs_sep = nn.ModuleList()
        self.convs_1x1 = nn.ModuleList()
        self.norms_1 = nn.ModuleList()
        self.norms_2 = nn.ModuleList()
        for i in range(n_layers):
            dilation = kernel_size ** i
            padding = (kernel_size * dilation - dilation) // 2
            self.convs_sep.append(nn.Conv1d(channels, channels, kernel_size,
                                            groups=channels, dilation=dilation, padding=padding
                                            ))
            self.convs_1x1.append(nn.Conv1d(channels, channels, 1))
            self.norms_1.append(LayerNorm(channels))
            self.norms_2.append(LayerNorm(channels))

    def forward(self, x, x_mask, g=None):
        if g is not None:
            x = x + g
        for i in range(self.n_layers):
            y = self.convs_sep[i](x * x_mask)
            y = self.norms_1[i](y)
            y = F.gelu(y)
            y = self.convs_1x1[i](y)
            y = self.norms_2[i](y)
            y = F.gelu(y)
            y = self.drop(y)
            x = x + y
        return x * x_mask


class WN(torch.nn.Module):
    def __init__(self, hidden_channels, kernel_size, dilation_rate, n_layers, gin_channels=0, p_dropout=0):
        super(WN, self).__init__()
        assert (kernel_size % 2 == 1)
        self.hidden_channels = hidden_channels
        self.kernel_size = kernel_size,
        self.dilation_rate = dilation_rate
        self.n_layers = n_layers
        self.gin_channels = gin_channels
        self.p_dropout = p_dropout

        self.in_layers = torch.nn.ModuleList()
        self.res_skip_layers = torch.nn.ModuleList()
        self.drop = nn.Dropout(p_dropout)

        if gin_channels != 0:
            cond_layer = torch.nn.Conv1d(gin_channels, 2 * hidden_channels * n_layers, 1)
            self.cond_layer = torch.nn.utils.weight_norm(cond_layer, name='weight')

        for i in range(n_layers):
            dilation = dilation_rate ** i
            padding = int((kernel_size * dilation - dilation) / 2)
            in_layer = torch.nn.Conv1d(hidden_channels, 2 * hidden_channels, kernel_size,
                                       dilation=dilation, padding=padding)
            in_layer = torch.nn.utils.weight_norm(in_layer, name='weight')
            self.in_layers.append(in_layer)

            # last one is not necessary
            if i < n_layers - 1:
                res_skip_channels = 2 * hidden_channels
            else:
                res_skip_channels = hidden_channels

            res_skip_layer = torch.nn.Conv1d(hidden_channels, res_skip_channels, 1)
            res_skip_layer = torch.nn.utils.weight_norm(res_skip_layer, name='weight')
            self.res_skip_layers.append(res_skip_layer)

    def forward(self, x, x_mask, g=None, **kwargs):
        output = torch.zeros_like(x)
        n_channels_tensor = torch.IntTensor([self.hidden_channels])

        if g is not None:
            g = self.cond_layer(g)

        for i in range(self.n_layers):
            x_in = self.in_layers[i](x)
            if g is not None:
                cond_offset = i * 2 * self.hidden_channels
                g_l = g[:, cond_offset:cond_offset + 2 * self.hidden_channels, :]
            else:
                g_l = torch.zeros_like(x_in)

            acts = commons.fused_add_tanh_sigmoid_multiply(
                x_in,
                g_l,
                n_channels_tensor)
            acts = self.drop(acts)

            res_skip_acts = self.res_skip_layers[i](acts)
            if i < self.n_layers - 1:
                res_acts = res_skip_acts[:, :self.hidden_channels, :]
                x = (x + res_acts) * x_mask
                output = output + res_skip_acts[:, self.hidden_channels:, :]
            else:
                output = output + res_skip_acts
        return output * x_mask

    def remove_weight_norm(self):
        if self.gin_channels != 0:
            torch.nn.utils.remove_weight_norm(self.cond_layer)
        for l in self.in_layers:
            torch.nn.utils.remove_weight_norm(l)
        for l in self.res_skip_layers:
            torch.nn.utils.remove_weight_norm(l)

class ResBlock1(torch.nn.Module):
    def __init__(self, channels, kernel_size=3, dilation=(1, 3, 5)):
        super(ResBlock1, self).__init__()
        self.convs1 = nn.ModuleList([
            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[0],
                               padding=get_padding(kernel_size, dilation[0]))),
            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[1],
                               padding=get_padding(kernel_size, dilation[1]))),
            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[2],
                               padding=get_padding(kernel_size, dilation[2])))
        ])
        self.convs1.apply(init_weights)

        self.convs2 = nn.ModuleList([
            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=1,
                               padding=get_padding(kernel_size, 1))),
            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=1,
                               padding=get_padding(kernel_size, 1))),
            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=1,
                               padding=get_padding(kernel_size, 1)))
        ])
        self.convs2.apply(init_weights)

    def forward(self, x, x_mask=None):
        for c1, c2 in zip(self.convs1, self.convs2):
            xt = F.leaky_relu(x, LRELU_SLOPE)
            if x_mask is not None:
                xt = xt * x_mask
            xt = c1(xt)
            xt = F.leaky_relu(xt, LRELU_SLOPE)
            if x_mask is not None:
                xt = xt * x_mask
            xt = c2(xt)
            x = xt + x
        if x_mask is not None:
            x = x * x_mask
        return x

    def remove_weight_norm(self):
        for l in self.convs1:
            remove_weight_norm(l)
        for l in self.convs2:
            remove_weight_norm(l)


class ResBlock2(torch.nn.Module):
    def __init__(self, channels, kernel_size=3, dilation=(1, 3)):
        super(ResBlock2, self).__init__()
        self.convs = nn.ModuleList([
            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[0],
                               padding=get_padding(kernel_size, dilation[0]))),
            weight_norm(Conv1d(channels, channels, kernel_size, 1, dilation=dilation[1],
                               padding=get_padding(kernel_size, dilation[1])))
        ])
        self.convs.apply(init_weights)

    def forward(self, x, x_mask=None):
        for c in self.convs:
            xt = F.leaky_relu(x, LRELU_SLOPE)
            if x_mask is not None:
                xt = xt * x_mask
            xt = c(xt)
            x = xt + x
        if x_mask is not None:
            x = x * x_mask
        return x

    def remove_weight_norm(self):
        for l in self.convs:
            remove_weight_norm(l)


class Log(nn.Module):
    def forward(self, x, x_mask, reverse=False, **kwargs):
        if not reverse:
            y = torch.log(torch.clamp_min(x, 1e-5)) * x_mask
            logdet = torch.sum(-y, [1, 2])
            return y, logdet
        else:
            x = torch.exp(x) * x_mask
            return x


class Flip(nn.Module):
    def forward(self, x, *args, reverse=False, **kwargs):
        x = torch.flip(x, [1])
        if not reverse:
            logdet = torch.zeros(x.size(0)).to(dtype=x.dtype, device=x.device)
            return x, logdet
        else:
            return x


class ElementwiseAffine(nn.Module):
    def __init__(self, channels):
        super().__init__()
        self.channels = channels
        self.m = nn.Parameter(torch.zeros(channels, 1))
        self.logs = nn.Parameter(torch.zeros(channels, 1))

    def forward(self, x, x_mask, reverse=False, **kwargs):
        if not reverse:
            y = self.m + torch.exp(self.logs) * x
            y = y * x_mask
            logdet = torch.sum(self.logs * x_mask, [1, 2])
            return y, logdet
        else:
            x = (x - self.m) * torch.exp(-self.logs) * x_mask
            return x


class ResidualCouplingLayer(nn.Module):
    def __init__(self,
                 channels,
                 hidden_channels,
                 kernel_size,
                 dilation_rate,
                 n_layers,
                 p_dropout=0,
                 gin_channels=0,
                 mean_only=False):
        assert channels % 2 == 0, "channels should be divisible by 2"
        super().__init__()
        self.channels = channels
        self.hidden_channels = hidden_channels
        self.kernel_size = kernel_size
        self.dilation_rate = dilation_rate
        self.n_layers = n_layers
        self.half_channels = channels // 2
        self.mean_only = mean_only

        self.pre = nn.Conv1d(self.half_channels, hidden_channels, 1)
        self.enc = WN(hidden_channels, kernel_size, dilation_rate, n_layers, p_dropout=p_dropout,
                      gin_channels=gin_channels)
        self.post = nn.Conv1d(hidden_channels, self.half_channels * (2 - mean_only), 1)
        self.post.weight.data.zero_()
        self.post.bias.data.zero_()

    def forward(self, x, x_mask, g=None, reverse=False):
        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
        h = self.pre(x0) * x_mask
        h = self.enc(h, x_mask, g=g)
        stats = self.post(h) * x_mask
        if not self.mean_only:
            m, logs = torch.split(stats, [self.half_channels] * 2, 1)
        else:
            m = stats
            logs = torch.zeros_like(m)

        if not reverse:
            x1 = m + x1 * torch.exp(logs) * x_mask
            x = torch.cat([x0, x1], 1)
            logdet = torch.sum(logs, [1, 2])
            return x, logdet
        else:
            x1 = (x1 - m) * torch.exp(-logs) * x_mask
            x = torch.cat([x0, x1], 1)
            return x
def modulate(x, shift, scale):
    return x * (1 + scale.unsqueeze(1)) + shift.unsqueeze(1)

def _ntuple(n):
    def parse(x):
        if isinstance(x, collections.abc.Iterable) and not isinstance(x, str):
            return tuple(x)
        return tuple(repeat(x, n))
    return parse
to_2tuple = _ntuple(2)

class FFN_Conv(nn.Module):
    """ MLP as used in Vision Transformer, MLP-Mixer and related networks
    """
    def __init__(
            self,
            in_features,
            hidden_features=None,
            out_features=None,
            act_layer=nn.GELU,
            norm_layer=None,
            bias=True,
            kernel=5,
            p_dropout=0.1
    ):
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        bias = to_2tuple(bias)

        self.fc1 = nn.Conv1d(in_features, hidden_features, kernel_size=kernel, stride=1, padding=(kernel-1)//2, bias=bias[0])
        self.act = act_layer()
        self.norm = norm_layer(hidden_features) if norm_layer is not None else nn.Identity()
        self.fc2 = nn.Conv1d(hidden_features, out_features, kernel_size=1, bias=bias[1])
        self.drop = nn.Dropout(p_dropout)

    def forward(self, x, x_mask):
        x = self.fc1(x.transpose(1,2))
        x = self.act(x)
        x = self.drop(x)
        x = self.fc2(x*x_mask) * x_mask
        x = self.drop(x) 
        return x.transpose(1,2)
    
class DiTConVBlock(nn.Module):
    """
    A DiT block with adaptive layer norm zero (adaLN-Zero) conditioning.
    """
    def __init__(self, hidden_size, num_heads, mlp_ratio=4.0, kernel=9, p_dropout=0.1, **block_kwargs):
        super().__init__()
        self.norm1 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
        self.attn = Attention(hidden_size, num_heads=num_heads, qkv_bias=True, **block_kwargs)
        self.norm2 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
        mlp_hidden_dim = int(hidden_size * mlp_ratio)
        approx_gelu = lambda: nn.GELU(approximate="tanh")
        self.mlp = FFN_Conv(in_features=hidden_size, hidden_features=mlp_hidden_dim, act_layer=approx_gelu, kernel=kernel, p_dropout=p_dropout)
        self.adaLN_modulation = nn.Sequential(
            nn.SiLU(),
            nn.Linear(hidden_size, 6 * hidden_size, bias=True)
        )
    def forward(self, x, c, x_mask):
        x = x*x_mask
        shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp = self.adaLN_modulation(c).chunk(6, dim=1)
        x = x + gate_msa.unsqueeze(1) * self.attn(modulate(self.norm1(x)*x_mask, shift_msa, scale_msa))*x_mask
        x = x + gate_mlp.unsqueeze(1) * self.mlp(modulate(self.norm2(x), shift_mlp, scale_mlp), x_mask.transpose(1,2))
        return x
class ResidualCouplingLayer_Transformer_simple(nn.Module):
    def __init__(self,
                 channels,
                 hidden_channels,
                 kernel_size,
                 dilation_rate,
                 n_layers,
                 p_dropout=0.1,
                 gin_channels=0,
                 mean_only=False,
                 attention_head=2):
        assert channels % 2 == 0, "channels should be divisible by 2"
        super().__init__()
        self.channels = channels
        self.hidden_channels = hidden_channels
        self.kernel_size = kernel_size
        self.dilation_rate = dilation_rate
        self.n_layers = n_layers
        self.half_channels = channels // 2
        self.mean_only = mean_only

        self.pre = nn.Conv1d(self.half_channels, hidden_channels, 1)

        self.enc_block = torch.nn.ModuleList([
            DiTConVBlock(hidden_channels, attention_head, mlp_ratio=4.0, kernel=5, p_dropout=p_dropout) for _ in range(n_layers)
        ])

        self.post = nn.Conv1d(hidden_channels, self.half_channels * (2 - mean_only), 1)
        
        self.initialize_weights()

        self.post.weight.data.zero_()
        self.post.bias.data.zero_()

    def initialize_weights(self):
    # Initialize transformer layers:
        def _basic_init(module):
            if isinstance(module, (nn.Conv1d, nn.Linear)):
                torch.nn.init.xavier_uniform_(module.weight)
                if module.bias is not None:
                    nn.init.constant_(module.bias, 0)

        self.apply(_basic_init)
        # Zero-out adaLN modulation layers in DiT blocks:
        for block in self.enc_block:
            nn.init.constant_(block.adaLN_modulation[-1].weight, 0)
            nn.init.constant_(block.adaLN_modulation[-1].bias, 0)

    def forward(self, x, x_mask, g=None, reverse=False):
        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
        h = self.pre(x0) * x_mask

        # h = self.enc(h, x_mask, g=g)
        h = h.transpose(1,2)
        x_mask = x_mask.transpose(1,2)

        for blk in self.enc_block:
            h = blk(h, g, x_mask)
        
        x_mask = x_mask.transpose(1,2)
        h = h.transpose(1,2)

        stats = self.post(h) * x_mask
        if not self.mean_only:
            m, logs = torch.split(stats, [self.half_channels] * 2, 1)
        else:
            m = stats
            logs = torch.zeros_like(m)

        if not reverse:
            x1 = m + x1 * torch.exp(logs) * x_mask
            x = torch.cat([x0, x1], 1)
            logdet = torch.sum(logs, [1, 2])
            return x, logdet
        else:
            x1 = (x1 - m) * torch.exp(-logs) * x_mask
            x = torch.cat([x0, x1], 1)
            return x

class ConvFlow(nn.Module):
    def __init__(self, in_channels, filter_channels, kernel_size, n_layers, num_bins=10, tail_bound=5.0):
        super().__init__()
        self.in_channels = in_channels
        self.filter_channels = filter_channels
        self.kernel_size = kernel_size
        self.n_layers = n_layers
        self.num_bins = num_bins
        self.tail_bound = tail_bound
        self.half_channels = in_channels // 2

        self.pre = nn.Conv1d(self.half_channels, filter_channels, 1)
        self.convs = DDSConv(filter_channels, kernel_size, n_layers, p_dropout=0.)
        self.proj = nn.Conv1d(filter_channels, self.half_channels * (num_bins * 3 - 1), 1)
        self.proj.weight.data.zero_()
        self.proj.bias.data.zero_()

    def forward(self, x, x_mask, g=None, reverse=False):
        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
        h = self.pre(x0)
        h = self.convs(h, x_mask, g=g)
        h = self.proj(h) * x_mask

        b, c, t = x0.shape
        h = h.reshape(b, c, -1, t).permute(0, 1, 3, 2)  # [b, cx?, t] -> [b, c, t, ?]

        unnormalized_widths = h[..., :self.num_bins] / math.sqrt(self.filter_channels)
        unnormalized_heights = h[..., self.num_bins:2 * self.num_bins] / math.sqrt(self.filter_channels)
        unnormalized_derivatives = h[..., 2 * self.num_bins:]

        x1, logabsdet = piecewise_rational_quadratic_transform(x1,
                                                               unnormalized_widths,
                                                               unnormalized_heights,
                                                               unnormalized_derivatives,
                                                               inverse=reverse,
                                                               tails='linear',
                                                               tail_bound=self.tail_bound
                                                               )

        x = torch.cat([x0, x1], 1) * x_mask
        logdet = torch.sum(logabsdet * x_mask, [1, 2])
        if not reverse:
            return x, logdet
        else:
            return x