diff options
Diffstat (limited to 'extensions-builtin/LDSR')
| -rw-r--r-- | extensions-builtin/LDSR/sd_hijack_autoencoder.py | 10 | ||||
| -rw-r--r-- | extensions-builtin/LDSR/sd_hijack_ddpm_v1.py | 14 |
2 files changed, 12 insertions, 12 deletions
diff --git a/extensions-builtin/LDSR/sd_hijack_autoencoder.py b/extensions-builtin/LDSR/sd_hijack_autoencoder.py index f457ca93..8cc82d54 100644 --- a/extensions-builtin/LDSR/sd_hijack_autoencoder.py +++ b/extensions-builtin/LDSR/sd_hijack_autoencoder.py @@ -24,7 +24,7 @@ class VQModel(pl.LightningModule): n_embed, embed_dim, ckpt_path=None, - ignore_keys=[], + ignore_keys=None, image_key="image", colorize_nlabels=None, monitor=None, @@ -62,7 +62,7 @@ class VQModel(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) + self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys or []) self.scheduler_config = scheduler_config self.lr_g_factor = lr_g_factor @@ -81,11 +81,11 @@ class VQModel(pl.LightningModule): if context is not None: print(f"{context}: Restored training weights") - def init_from_ckpt(self, path, ignore_keys=list()): + def init_from_ckpt(self, path, ignore_keys=None): sd = torch.load(path, map_location="cpu")["state_dict"] keys = list(sd.keys()) for k in keys: - for ik in ignore_keys: + for ik in ignore_keys or []: if k.startswith(ik): print("Deleting key {} from state_dict.".format(k)) del sd[k] @@ -270,7 +270,7 @@ class VQModel(pl.LightningModule): class VQModelInterface(VQModel): def __init__(self, embed_dim, *args, **kwargs): - super().__init__(embed_dim=embed_dim, *args, **kwargs) + super().__init__(*args, embed_dim=embed_dim, **kwargs) self.embed_dim = embed_dim def encode(self, x): diff --git a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py index d8fc30e3..f16d6504 100644 --- a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py +++ b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py @@ -48,7 +48,7 @@ class DDPMV1(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, @@ -100,7 +100,7 @@ class DDPMV1(pl.LightningModule): if monitor is not None: self.monitor = monitor 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) self.register_schedule(given_betas=given_betas, beta_schedule=beta_schedule, timesteps=timesteps, linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s) @@ -182,13 +182,13 @@ class DDPMV1(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): sd = torch.load(path, map_location="cpu") if "state_dict" in list(sd.keys()): sd = sd["state_dict"] keys = list(sd.keys()) for k in keys: - for ik in ignore_keys: + for ik in ignore_keys or []: if k.startswith(ik): print("Deleting key {} from state_dict.".format(k)) del sd[k] @@ -444,7 +444,7 @@ class LatentDiffusionV1(DDPMV1): conditioning_key = None ckpt_path = kwargs.pop("ckpt_path", None) ignore_keys = kwargs.pop("ignore_keys", []) - super().__init__(conditioning_key=conditioning_key, *args, **kwargs) + super().__init__(*args, conditioning_key=conditioning_key, **kwargs) self.concat_mode = concat_mode self.cond_stage_trainable = cond_stage_trainable self.cond_stage_key = cond_stage_key @@ -1418,10 +1418,10 @@ class Layout2ImgDiffusionV1(LatentDiffusionV1): # 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] |