import torch
import torch.nn as nn
import numpy as np
from functools import partial
from ldm.modules.diffusionmodules.util import make_beta_schedule





class DDPM(nn.Module):
    def __init__(self, beta_schedule="linear", timesteps=1000, linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
        super().__init__()

        self.v_posterior = 0 
        self.register_schedule(beta_schedule, timesteps, linear_start, linear_end, cosine_s)


    def register_schedule(self, beta_schedule="linear", timesteps=1000, linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
        
        betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s)
        alphas = 1. - betas
        alphas_cumprod = np.cumprod(alphas, axis=0)
        alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1])

        timesteps, = betas.shape
        self.num_timesteps = int(timesteps)
        self.linear_start = linear_start
        self.linear_end = linear_end
        assert alphas_cumprod.shape[0] == self.num_timesteps, 'alphas have to be defined for each timestep'

        to_torch = partial(torch.tensor, dtype=torch.float32)

        self.register_buffer('betas', to_torch(betas))
        self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
        self.register_buffer('alphas_cumprod_prev', to_torch(alphas_cumprod_prev))

        # calculations for diffusion q(x_t | x_{t-1}) and others
        self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod)))
        self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod)))
        self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod)))
        self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod)))
        self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod - 1)))

        # calculations for posterior q(x_{t-1} | x_t, x_0)
        posterior_variance = (1 - self.v_posterior) * betas * (1. - alphas_cumprod_prev) / ( 1. - alphas_cumprod) + self.v_posterior * betas
        # above: equal to 1. / (1. / (1. - alpha_cumprod_tm1) + alpha_t / beta_t)
        
        self.register_buffer('posterior_variance', to_torch(posterior_variance))
        
        # below: log calculation clipped because the posterior variance is 0 at the beginning of the diffusion chain
        self.register_buffer('posterior_log_variance_clipped', to_torch(np.log(np.maximum(posterior_variance, 1e-20))))
        self.register_buffer('posterior_mean_coef1', to_torch( betas * np.sqrt(alphas_cumprod_prev) / (1. - alphas_cumprod)))
        self.register_buffer('posterior_mean_coef2', to_torch( (1. - alphas_cumprod_prev) * np.sqrt(alphas) / (1. - alphas_cumprod)))