ls_mlkit.diffusion.base_diffuser module

class ls_mlkit.diffusion.base_diffuser.BaseDiffuser(config: BaseDiffuserConfig, time_scheduler: DiffusionTimeScheduler)

Bases: BaseGenerativeModel

abstract method:

abstractmethod forward_process(x_0: Tensor, discrete_t: Tensor, mask: Tensor, *args: list[Any], **kwargs: dict[Any, Any]) → dict

Forward process, from \(x_0\) to \(x_t\)

Parameters:

• x_0 (Tensor) – \(x_0\)

• discrete_t (Tensor) – the discrete time steps \(t\)

• mask (Tensor) – the mask of the sample

Returns:

a dictionary that must contain the key “x_t”

Return type:

dict

class ls_mlkit.diffusion.base_diffuser.BaseDiffuserConfig(ndim_micro_shape: int, n_discretization_steps: int, n_inference_steps: int = None, use_batch_flattening: bool = False, *args: list[Any], **kwargs: dict[Any, Any])

Bases: BaseGenerativeModelConfig