Shortcuts

mmedit.models.editors.ddpm.ddpm_scheduler

Module Contents

Classes

DDPMScheduler

class mmedit.models.editors.ddpm.ddpm_scheduler.DDPMScheduler(num_train_timesteps: int = 1000, beta_start: float = 0.0001, beta_end: float = 0.02, beta_schedule: str = 'linear', trained_betas: Optional[Union[numpy.array, list]] = None, variance_type='fixed_small', clip_sample=True)[source]
set_timesteps(num_inference_steps)[source]

set timesteps.

_get_variance(t, predicted_variance=None, variance_type=None)[source]

get variance.

step(model_output: torch.FloatTensor, timestep: int, sample: torch.FloatTensor, predict_epsilon=True, cond_fn=None, cond_kwargs={}, generator=None)[source]
add_noise(original_samples, noise, timesteps)[source]

add noise.

abstract training_loss(model, x_0, t)[source]
abstract sample_timestep()[source]
__len__()[source]
Read the Docs v: latest
Versions
master
latest
stable
zyh-re-docs
zyh-doc-notfound-extend
zyh-api-rendering
Downloads
pdf
epub
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.