diff options
Diffstat (limited to 'modules/models/diffusion/ddpm_edit.py')
| -rw-r--r-- | modules/models/diffusion/ddpm_edit.py | 52 |
1 files changed, 24 insertions, 28 deletions
diff --git a/modules/models/diffusion/ddpm_edit.py b/modules/models/diffusion/ddpm_edit.py index f880bc3c..3fb76b65 100644 --- a/modules/models/diffusion/ddpm_edit.py +++ b/modules/models/diffusion/ddpm_edit.py @@ -52,7 +52,7 @@ class DDPM(pl.LightningModule): beta_schedule="linear", loss_type="l2", ckpt_path=None, - ignore_keys=[], + ignore_keys=None, load_only_unet=False, monitor="val/loss", use_ema=True, @@ -107,7 +107,7 @@ class DDPM(pl.LightningModule): print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.") if ckpt_path is not None: - self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet) + self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys or [], only_model=load_only_unet) # If initialing from EMA-only checkpoint, create EMA model after loading. if self.use_ema and not load_ema: @@ -194,7 +194,9 @@ class DDPM(pl.LightningModule): if context is not None: print(f"{context}: Restored training weights") - def init_from_ckpt(self, path, ignore_keys=list(), only_model=False): + def init_from_ckpt(self, path, ignore_keys=None, only_model=False): + ignore_keys = ignore_keys or [] + sd = torch.load(path, map_location="cpu") if "state_dict" in list(sd.keys()): sd = sd["state_dict"] @@ -403,7 +405,7 @@ class DDPM(pl.LightningModule): @torch.no_grad() def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs): - log = dict() + log = {} x = self.get_input(batch, self.first_stage_key) N = min(x.shape[0], N) n_row = min(x.shape[0], n_row) @@ -411,7 +413,7 @@ class DDPM(pl.LightningModule): log["inputs"] = x # get diffusion row - diffusion_row = list() + diffusion_row = [] x_start = x[:n_row] for t in range(self.num_timesteps): @@ -473,13 +475,13 @@ class LatentDiffusion(DDPM): conditioning_key = None ckpt_path = kwargs.pop("ckpt_path", None) ignore_keys = kwargs.pop("ignore_keys", []) - super().__init__(conditioning_key=conditioning_key, *args, load_ema=load_ema, **kwargs) + super().__init__(*args, conditioning_key=conditioning_key, load_ema=load_ema, **kwargs) self.concat_mode = concat_mode self.cond_stage_trainable = cond_stage_trainable self.cond_stage_key = cond_stage_key try: self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1 - except: + except Exception: self.num_downs = 0 if not scale_by_std: self.scale_factor = scale_factor @@ -891,16 +893,6 @@ class LatentDiffusion(DDPM): c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float())) return self.p_losses(x, c, t, *args, **kwargs) - def _rescale_annotations(self, bboxes, crop_coordinates): # TODO: move to dataset - def rescale_bbox(bbox): - x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2]) - y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3]) - w = min(bbox[2] / crop_coordinates[2], 1 - x0) - h = min(bbox[3] / crop_coordinates[3], 1 - y0) - return x0, y0, w, h - - return [rescale_bbox(b) for b in bboxes] - def apply_model(self, x_noisy, t, cond, return_ids=False): if isinstance(cond, dict): @@ -1140,7 +1132,7 @@ class LatentDiffusion(DDPM): if cond is not None: if isinstance(cond, dict): cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else - list(map(lambda x: x[:batch_size], cond[key])) for key in cond} + [x[:batch_size] for x in cond[key]] for key in cond} else: cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size] @@ -1171,8 +1163,10 @@ class LatentDiffusion(DDPM): if i % log_every_t == 0 or i == timesteps - 1: intermediates.append(x0_partial) - if callback: callback(i) - if img_callback: img_callback(img, i) + if callback: + callback(i) + if img_callback: + img_callback(img, i) return img, intermediates @torch.no_grad() @@ -1219,8 +1213,10 @@ class LatentDiffusion(DDPM): if i % log_every_t == 0 or i == timesteps - 1: intermediates.append(img) - if callback: callback(i) - if img_callback: img_callback(img, i) + if callback: + callback(i) + if img_callback: + img_callback(img, i) if return_intermediates: return img, intermediates @@ -1235,7 +1231,7 @@ class LatentDiffusion(DDPM): if cond is not None: if isinstance(cond, dict): cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else - list(map(lambda x: x[:batch_size], cond[key])) for key in cond} + [x[:batch_size] for x in cond[key]] for key in cond} else: cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size] return self.p_sample_loop(cond, @@ -1267,7 +1263,7 @@ class LatentDiffusion(DDPM): use_ddim = False - log = dict() + log = {} z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key, return_first_stage_outputs=True, force_c_encode=True, @@ -1295,7 +1291,7 @@ class LatentDiffusion(DDPM): if plot_diffusion_rows: # get diffusion row - diffusion_row = list() + diffusion_row = [] z_start = z[:n_row] for t in range(self.num_timesteps): if t % self.log_every_t == 0 or t == self.num_timesteps - 1: @@ -1337,7 +1333,7 @@ class LatentDiffusion(DDPM): if inpaint: # make a simple center square - b, h, w = z.shape[0], z.shape[2], z.shape[3] + h, w = z.shape[2], z.shape[3] mask = torch.ones(N, h, w).to(self.device) # zeros will be filled in mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0. @@ -1439,10 +1435,10 @@ class Layout2ImgDiffusion(LatentDiffusion): # TODO: move all layout-specific hacks to this class def __init__(self, cond_stage_key, *args, **kwargs): assert cond_stage_key == 'coordinates_bbox', 'Layout2ImgDiffusion only for cond_stage_key="coordinates_bbox"' - super().__init__(cond_stage_key=cond_stage_key, *args, **kwargs) + super().__init__(*args, cond_stage_key=cond_stage_key, **kwargs) def log_images(self, batch, N=8, *args, **kwargs): - logs = super().log_images(batch=batch, N=N, *args, **kwargs) + logs = super().log_images(*args, batch=batch, N=N, **kwargs) key = 'train' if self.training else 'validation' dset = self.trainer.datamodule.datasets[key] |