Create a sampling function. Args: config: A `ml_collections.ConfigDict` object that contains all configuration information. sde: A `sde_lib.SDE` object that represents the forward SDE. shape: A sequence of integers representing the expected shape of a single sample. inverse_scaler
(config, sde, shape, inverse_scaler, eps)
source not stored for this graph (policy: none)
nothing calls this directly
no test coverage detected