From 1c0fca1317e24b93e1d74400ffbc77ed04211564 Mon Sep 17 00:00:00 2001 From: smthemex <138738845+smthemex@users.noreply.github.com> Date: Wed, 22 May 2024 10:44:08 +0800 Subject: [PATCH] Delete custom_net/ddim.py change --- custom_net/ddim.py | 343 --------------------------------------------- 1 file changed, 343 deletions(-) delete mode 100644 custom_net/ddim.py diff --git a/custom_net/ddim.py b/custom_net/ddim.py deleted file mode 100644 index 32f8e15..0000000 --- a/custom_net/ddim.py +++ /dev/null @@ -1,343 +0,0 @@ -"""SAMPLING ONLY.""" - -import torch -import numpy as np -from tqdm import tqdm -from functools import partial -from einops import rearrange - -from ..customnet_modules.util import make_ddim_sampling_parameters, make_ddim_timesteps, noise_like, extract_into_tensor -from ..models.sampling_util import renorm_thresholding, norm_thresholding, spatial_norm_thresholding - - -class DDIMSampler(object): - def __init__(self, model, schedule="linear", **kwargs): - super().__init__() - self.model = model - self.ddpm_num_timesteps = model.num_timesteps - self.schedule = schedule - - def to(self, device): - """Same as to in torch module - Don't really underestand why this isn't a module in the first place""" - for k, v in self.__dict__.items(): - if isinstance(v, torch.Tensor): - new_v = getattr(self, k).to(device) - setattr(self, k, new_v) - - - def register_buffer(self, name, attr): - if type(attr) == torch.Tensor: - if attr.device != torch.device("cuda"): - attr = attr.to(torch.device("cuda")) - setattr(self, name, attr) - - def make_schedule(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True): - self.ddim_timesteps = make_ddim_timesteps(ddim_discr_method=ddim_discretize, num_ddim_timesteps=ddim_num_steps, - num_ddpm_timesteps=self.ddpm_num_timesteps,verbose=verbose) - alphas_cumprod = self.model.alphas_cumprod - assert alphas_cumprod.shape[0] == self.ddpm_num_timesteps, 'alphas have to be defined for each timestep' - to_torch = lambda x: x.clone().detach().to(torch.float32).to(self.model.device) - - self.register_buffer('betas', to_torch(self.model.betas)) - self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod)) - self.register_buffer('alphas_cumprod_prev', to_torch(self.model.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.cpu()))) - self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod.cpu()))) - self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod.cpu()))) - self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu()))) - self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu() - 1))) - - # ddim sampling parameters - ddim_sigmas, ddim_alphas, ddim_alphas_prev = make_ddim_sampling_parameters(alphacums=alphas_cumprod.cpu(), - ddim_timesteps=self.ddim_timesteps, - eta=ddim_eta,verbose=verbose) - self.register_buffer('ddim_sigmas', ddim_sigmas) - self.register_buffer('ddim_alphas', ddim_alphas) - self.register_buffer('ddim_alphas_prev', ddim_alphas_prev) - self.register_buffer('ddim_sqrt_one_minus_alphas', np.sqrt(1. - ddim_alphas)) - sigmas_for_original_sampling_steps = ddim_eta * torch.sqrt( - (1 - self.alphas_cumprod_prev) / (1 - self.alphas_cumprod) * ( - 1 - self.alphas_cumprod / self.alphas_cumprod_prev)) - self.register_buffer('ddim_sigmas_for_original_num_steps', sigmas_for_original_sampling_steps) - - @torch.no_grad() - def sample(self, - S, - batch_size, - shape, - conditioning=None, - callback=None, - normals_sequence=None, - img_callback=None, - quantize_x0=False, - eta=0., - mask=None, - x0=None, - temperature=1., - noise_dropout=0., - score_corrector=None, - corrector_kwargs=None, - verbose=True, - x_T=None, - log_every_t=100, - unconditional_guidance_scale=1., - unconditional_conditioning=None, # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ... - dynamic_threshold=None, - **kwargs - ): - if conditioning is not None: - if isinstance(conditioning, dict): - ctmp = conditioning[list(conditioning.keys())[0]] - while isinstance(ctmp, list): ctmp = ctmp[0] - cbs = ctmp.shape[0] - if cbs != batch_size: - print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}") - - else: - if conditioning.shape[0] != batch_size: - print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}") - - self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose) - # sampling - C, H, W = shape - size = (batch_size, C, H, W) - print(f'Data shape for DDIM sampling is {size}, eta {eta}') - - samples, intermediates = self.ddim_sampling(conditioning, size, - callback=callback, - img_callback=img_callback, - quantize_denoised=quantize_x0, - mask=mask, x0=x0, - ddim_use_original_steps=False, - noise_dropout=noise_dropout, - temperature=temperature, - score_corrector=score_corrector, - corrector_kwargs=corrector_kwargs, - x_T=x_T, - log_every_t=log_every_t, - unconditional_guidance_scale=unconditional_guidance_scale, - unconditional_conditioning=unconditional_conditioning, - dynamic_threshold=dynamic_threshold, - **kwargs) - return samples, intermediates - - @torch.no_grad() - def ddim_sampling(self, cond, shape, - x_T=None, ddim_use_original_steps=False, - callback=None, timesteps=None, quantize_denoised=False, - mask=None, x0=None, img_callback=None, log_every_t=100, - temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None, - unconditional_guidance_scale=1., unconditional_conditioning=None, dynamic_threshold=None, - t_start=-1, - **kwargs): - device = self.model.betas.device - b = shape[0] - if x_T is None: - img = torch.randn(shape, device=device) - else: - img = x_T - - if timesteps is None: - timesteps = self.ddpm_num_timesteps if ddim_use_original_steps else self.ddim_timesteps - elif timesteps is not None and not ddim_use_original_steps: - subset_end = int(min(timesteps / self.ddim_timesteps.shape[0], 1) * self.ddim_timesteps.shape[0]) - 1 - timesteps = self.ddim_timesteps[:subset_end] - - timesteps = timesteps[:t_start] - - intermediates = {'x_inter': [img], 'pred_x0': [img]} - time_range = reversed(range(0,timesteps)) if ddim_use_original_steps else np.flip(timesteps) - total_steps = timesteps if ddim_use_original_steps else timesteps.shape[0] - print(f"Running DDIM Sampling with {total_steps} timesteps") - - iterator = tqdm(time_range, desc='DDIM Sampler', total=total_steps) - - for i, step in enumerate(iterator): - index = total_steps - i - 1 - ts = torch.full((b,), step, device=device, dtype=torch.long) - - if mask is not None: - assert x0 is not None - img_orig = self.model.q_sample(x0, ts) # TODO: deterministic forward pass? - img = img_orig * mask + (1. - mask) * img - - outs = self.p_sample_ddim(img, cond, ts, index=index, use_original_steps=ddim_use_original_steps, - quantize_denoised=quantize_denoised, temperature=temperature, - noise_dropout=noise_dropout, score_corrector=score_corrector, - corrector_kwargs=corrector_kwargs, - unconditional_guidance_scale=unconditional_guidance_scale, - unconditional_conditioning=unconditional_conditioning, - dynamic_threshold=dynamic_threshold, - **kwargs) - img, pred_x0 = outs - if callback: - img = callback(i, img, pred_x0) - if img_callback: img_callback(pred_x0, i) - - if index % log_every_t == 0 or index == total_steps - 1: - intermediates['x_inter'].append(img) - intermediates['pred_x0'].append(pred_x0) - - return img, intermediates - - @torch.no_grad() - def p_sample_ddim(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False, - temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None, - unconditional_guidance_scale=1., unconditional_conditioning=None, - dynamic_threshold=None, **kwargs): - b, *_, device = *x.shape, x.device - - - if unconditional_conditioning is None or unconditional_guidance_scale == 1.: - e_t = self.model.apply_model(x, t, c) - else: - cfg_type = kwargs.get("cfg_type", 0) - cfg = kwargs.get("cfg_scale_dict", {"img": 0., "text":0., "all": 3.0 }) - truncate_step = kwargs.get("cfg_type", 250) ## 250 -1 - - if cfg_type == 0 : - model_t = self.model.apply_model(x, t, c) - - model_uc = self.model.apply_model(x, t, unconditional_conditioning) - - e_t = model_uc + cfg["all"]*(model_t - model_uc) - - elif cfg_type==1: - - model_t = self.model.apply_model(x, t, c) - - c_text = {"c_concat": unconditional_conditioning["c_concat"], - "c_crossattn": [unconditional_conditioning["c_crossattn"][0], - c["c_crossattn"][1],]} - - c_img = {"c_concat": c["c_concat"], - "c_crossattn": [c["c_crossattn"][0], - unconditional_conditioning["c_crossattn"][1],]} - - model_t_text = self.model.apply_model(x, t, c_text) - model_t_img = self.model.apply_model(x, t, c_img) - model_uc = self.model.apply_model(x, t, unconditional_conditioning) - - e_t = model_uc + cfg["all"]*(model_t - model_uc) - if t[0] > truncate_step: - print(1, t[0]) - e_t += cfg["img"] * (model_t_img - model_uc) - e_t += cfg["text"] * (model_t_text - model_uc) - - - if score_corrector is not None: - assert self.model.parameterization == "eps" - e_t = score_corrector.modify_score(self.model, e_t, x, t, c, **corrector_kwargs) - - alphas = self.model.alphas_cumprod if use_original_steps else self.ddim_alphas - alphas_prev = self.model.alphas_cumprod_prev if use_original_steps else self.ddim_alphas_prev - sqrt_one_minus_alphas = self.model.sqrt_one_minus_alphas_cumprod if use_original_steps else self.ddim_sqrt_one_minus_alphas - sigmas = self.model.ddim_sigmas_for_original_num_steps if use_original_steps else self.ddim_sigmas - # select parameters corresponding to the currently considered timestep - a_t = torch.full((b, 1, 1, 1), alphas[index], device=device) - a_prev = torch.full((b, 1, 1, 1), alphas_prev[index], device=device) - sigma_t = torch.full((b, 1, 1, 1), sigmas[index], device=device) - sqrt_one_minus_at = torch.full((b, 1, 1, 1), sqrt_one_minus_alphas[index],device=device) - - # current prediction for x_0 - pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt() - if quantize_denoised: - pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0) - - if dynamic_threshold is not None: - pred_x0 = norm_thresholding(pred_x0, dynamic_threshold) - - # direction pointing to x_t - dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t - noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature - if noise_dropout > 0.: - noise = torch.nn.functional.dropout(noise, p=noise_dropout) - x_prev = a_prev.sqrt() * pred_x0 + dir_xt + noise - return x_prev, pred_x0 - - @torch.no_grad() - def encode(self, x0, c, t_enc, use_original_steps=False, return_intermediates=None, - unconditional_guidance_scale=1.0, unconditional_conditioning=None): - num_reference_steps = self.ddpm_num_timesteps if use_original_steps else self.ddim_timesteps.shape[0] - - assert t_enc <= num_reference_steps - num_steps = t_enc - - if use_original_steps: - alphas_next = self.alphas_cumprod[:num_steps] - alphas = self.alphas_cumprod_prev[:num_steps] - else: - alphas_next = self.ddim_alphas[:num_steps] - alphas = torch.tensor(self.ddim_alphas_prev[:num_steps]) - - x_next = x0 - intermediates = [] - inter_steps = [] - for i in tqdm(range(num_steps), desc='Encoding Image'): - t = torch.full((x0.shape[0],), i, device=self.model.device, dtype=torch.long) - if unconditional_guidance_scale == 1.: - noise_pred = self.model.apply_model(x_next, t, c) - else: - assert unconditional_conditioning is not None - e_t_uncond, noise_pred = torch.chunk( - self.model.apply_model(torch.cat((x_next, x_next)), torch.cat((t, t)), - torch.cat((unconditional_conditioning, c))), 2) - noise_pred = e_t_uncond + unconditional_guidance_scale * (noise_pred - e_t_uncond) - - xt_weighted = (alphas_next[i] / alphas[i]).sqrt() * x_next - weighted_noise_pred = alphas_next[i].sqrt() * ( - (1 / alphas_next[i] - 1).sqrt() - (1 / alphas[i] - 1).sqrt()) * noise_pred - x_next = xt_weighted + weighted_noise_pred - if return_intermediates and i % ( - num_steps // return_intermediates) == 0 and i < num_steps - 1: - intermediates.append(x_next) - inter_steps.append(i) - elif return_intermediates and i >= num_steps - 2: - intermediates.append(x_next) - inter_steps.append(i) - - out = {'x_encoded': x_next, 'intermediate_steps': inter_steps} - if return_intermediates: - out.update({'intermediates': intermediates}) - return x_next, out - - @torch.no_grad() - def stochastic_encode(self, x0, t, use_original_steps=False, noise=None): - # fast, but does not allow for exact reconstruction - # t serves as an index to gather the correct alphas - if use_original_steps: - sqrt_alphas_cumprod = self.sqrt_alphas_cumprod - sqrt_one_minus_alphas_cumprod = self.sqrt_one_minus_alphas_cumprod - else: - sqrt_alphas_cumprod = torch.sqrt(self.ddim_alphas) - sqrt_one_minus_alphas_cumprod = self.ddim_sqrt_one_minus_alphas - - if noise is None: - noise = torch.randn_like(x0) - return (extract_into_tensor(sqrt_alphas_cumprod, t, x0.shape) * x0 + - extract_into_tensor(sqrt_one_minus_alphas_cumprod, t, x0.shape) * noise) - - @torch.no_grad() - def decode(self, x_latent, cond, t_start, unconditional_guidance_scale=1.0, unconditional_conditioning=None, - use_original_steps=False): - - timesteps = np.arange(self.ddpm_num_timesteps) if use_original_steps else self.ddim_timesteps - timesteps = timesteps[:t_start] - - time_range = np.flip(timesteps) - total_steps = timesteps.shape[0] - print(f"Running DDIM Sampling with {total_steps} timesteps") - - iterator = tqdm(time_range, desc='Decoding image', total=total_steps) - x_dec = x_latent - for i, step in enumerate(iterator): - index = total_steps - i - 1 - ts = torch.full((x_latent.shape[0],), step, device=x_latent.device, dtype=torch.long) - x_dec, _ = self.p_sample_ddim(x_dec, cond, ts, index=index, use_original_steps=use_original_steps, - unconditional_guidance_scale=unconditional_guidance_scale, - unconditional_conditioning=unconditional_conditioning) - return x_dec -