<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/experimental/bijectors/__init__.py) |

TensorFlow Probability experimental bijectors package.

## Classes

[`class HighwayFlow`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/bijectors/HighwayFlow): Implements an Highway Flow bijector \[1\].

[`class ScalarFunctionWithInferredInverse`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/bijectors/ScalarFunctionWithInferredInverse): Bijector to associate a numeric inverse with any invertible function.

[`class Sharded`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/bijectors/Sharded): A meta-bijector meant for use in an SPMD distributed context.

## Functions

[`build_trainable_highway_flow(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/bijectors/build_trainable_highway_flow): Builds a HighwayFlow parameterized by trainable variables.

[`forward_log_det_jacobian_ratio(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/bijectors/forward_log_det_jacobian_ratio): Computes `p.fldj(x, ndims) - q.fdlj(y, ndims)`, numerically stably.

[`inverse_log_det_jacobian_ratio(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/bijectors/inverse_log_det_jacobian_ratio): Computes `p.ildj(x, ndims) - q.idlj(y, ndims)`, numerically stably.

[`make_distribution_bijector(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/bijectors/make_distribution_bijector): Builds a bijector to approximately transform `N(0, 1)` into `distribution`.