renaming and formatting

sbi/inference/posteriors/score_posterior.py

@@ -144,7 +144,7 @@ def sample(
 
         if self.sample_with == "ode":
             samples = rejection.accept_reject_sample(
-                proposal=self.sample_via_zuko,
+                proposal=self.sample_via_ode,
                 accept_reject_fn=lambda theta: within_support(self.prior, theta),
                 num_samples=num_samples,
                 show_progress_bars=show_progress_bars,
@@ -241,7 +241,7 @@ def _sample_via_diffusion(
 
         return samples
 
-    def sample_via_zuko(
+    def sample_via_ode(
         self,
         sample_shape: Shape = torch.Size(),
     ) -> Tensor:
@@ -333,7 +333,7 @@ def sample_batched(
 
         if self.sample_with == "ode":
             samples = rejection.accept_reject_sample(
-                proposal=self.sample_via_zuko,
+                proposal=self.sample_via_ode,
                 accept_reject_fn=lambda theta: within_support(self.prior, theta),
                 num_samples=num_samples,
                 num_xos=batch_size,

sbi/inference/potentials/score_based_potential.py

@@ -1,5 +1,6 @@
 # This file is part of sbi, a toolkit for simulation-based inference. sbi is licensed
 # under the Apache License Version 2.0, see <https://www.apache.org/licenses/>
+
 from functools import partial
 from typing import Optional, Tuple
 

sbi/samplers/score/diffuser.py

@@ -101,9 +101,6 @@ def initialize(self, num_samples: int) -> Tensor:
         # iid_bridge is not accurate.
         num_batch = self.batch_shape.numel()
         init_shape = (num_samples, num_batch) + self.input_shape
-        # init_shape = (
-        #     num_samples,
-        # ) + self.input_shape  # just use num_samples, not num_batch
         # NOTE: for the IID setting we might need to scale the noise with iid batch
         # size, as in equation (7) in the paper.
         eps = torch.randn(init_shape, device=self.device)