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

def init_weights(m, mean=0.0, std=0.01):
  classname = m.__class__.__name__
  if classname.find("Conv") != -1:
    m.weight.data.normal_(mean, std)


def get_padding(kernel_size, dilation=1):
  return int((kernel_size*dilation - dilation)/2)


def intersperse(lst, item):
  # needed for inference
  result = [item] * (len(lst) * 2 + 1)
  result[1::2] = lst
  return result


def kl_divergence(m_p, logs_p, m_q, logs_q):
  """KL(P||Q)"""
  kl = (logs_q - logs_p) - 0.5
  kl += 0.5 * (torch.exp(2. * logs_p) + ((m_p - m_q)**2)) * torch.exp(-2. * logs_q)
  return kl


def rand_gumbel(shape):
  """Sample from the Gumbel distribution, protect from overflows."""
  uniform_samples = torch.rand(shape) * 0.99998 + 0.00001
  return -torch.log(-torch.log(uniform_samples))


@torch.jit.script
def fused_add_tanh_sigmoid_multiply(input_a, input_b, n_channels):
  n_channels_int = n_channels[0]
  in_act = input_a + input_b
  t_act = torch.tanh(in_act[:, :n_channels_int, :])
  s_act = torch.sigmoid(in_act[:, n_channels_int:, :])
  acts = t_act * s_act
  return acts


def convert_pad_shape(pad_shape):
  l = pad_shape[::-1]
  pad_shape = [item for sublist in l for item in sublist]
  return pad_shape


def sequence_mask(length, max_length=None):
  if max_length is None:
    max_length = length.max()
  x = torch.arange(max_length, dtype=length.dtype, device=length.device)
  return x.unsqueeze(0) < length.unsqueeze(1)


def generate_path(duration, mask):
  """
  duration: [b, 1, t_x]
  mask: [b, 1, t_y, t_x]
  """
  device = duration.device
  
  b, _, t_y, t_x = mask.shape
  cum_duration = torch.cumsum(duration, -1)
  
  cum_duration_flat = cum_duration.view(b * t_x)
  path = sequence_mask(cum_duration_flat, t_y).to(mask.dtype)
  path = path.view(b, t_x, t_y)
  path = path - F.pad(path, convert_pad_shape([[0, 0], [1, 0], [0, 0]]))[:, :-1]
  path = path.unsqueeze(1).transpose(2,3) * mask
  return path