Skip to content

allow tensor in DiagonalNormal dimension #571

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Sep 10, 2025
Merged

allow tensor in DiagonalNormal dimension #571

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
82b3ab4
allow tensor in DiagonalNormal dimension
arrjon Sep 6, 2025
8fbf737
fix sum dims
arrjon Sep 7, 2025
5c27246
fix batch_shape for sample
arrjon Sep 7, 2025
c684bca
dims to tuple
arrjon Sep 7, 2025
e55631d
fix batch_shape in sample
arrjon Sep 9, 2025
3eaff24
fix batch_shape for point approximator
arrjon Sep 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion bayesflow/approximators/continuous_approximator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -535,7 +535,10 @@ def _sample(
inference_conditions = keras.ops.broadcast_to(
inference_conditions, (batch_size, num_samples, *keras.ops.shape(inference_conditions)[2:])
)
batch_shape = keras.ops.shape(inference_conditions)[:-1]
batch_shape = (
batch_size,
num_samples,
)
else:
batch_shape = (num_samples,)

Expand Down
12 changes: 6 additions & 6 deletions bayesflow/distributions/diagonal_normal.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,18 +57,18 @@ def __init__(
self.trainable_parameters = trainable_parameters
self.seed_generator = seed_generator or keras.random.SeedGenerator()

self.dim = None
self.dims = None
self._mean = None
self._std = None

def build(self, input_shape: Shape) -> None:
if self.built:
return

self.dim = int(input_shape[-1])
self.dims = tuple(input_shape[1:])

self.mean = ops.cast(ops.broadcast_to(self.mean, (self.dim,)), "float32")
self.std = ops.cast(ops.broadcast_to(self.std, (self.dim,)), "float32")
self.mean = ops.cast(ops.broadcast_to(self.mean, self.dims), "float32")
self.std = ops.cast(ops.broadcast_to(self.std, self.dims), "float32")

if self.trainable_parameters:
self._mean = self.add_weight(
Expand All @@ -91,14 +91,14 @@ def log_prob(self, samples: Tensor, *, normalize: bool = True) -> Tensor:
result = -0.5 * ops.sum((samples - self._mean) ** 2 / self._std**2, axis=-1)

if normalize:
log_normalization_constant = -0.5 * self.dim * math.log(2.0 * math.pi) - ops.sum(ops.log(self._std))
log_normalization_constant = -0.5 * sum(self.dims) * math.log(2.0 * math.pi) - ops.sum(ops.log(self._std))
result += log_normalization_constant

return result

@allow_batch_size
def sample(self, batch_shape: Shape) -> Tensor:
return self._mean + self._std * keras.random.normal(shape=batch_shape + (self.dim,), seed=self.seed_generator)
return self._mean + self._std * keras.random.normal(shape=batch_shape + self.dims, seed=self.seed_generator)

def get_config(self):
base_config = super().get_config()
Expand Down
Loading