# Module: tf.contrib.distributions.bijectors

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/contrib/distributions/python/ops/bijectors/__init__.py) |

Bijector Ops.

Use [tfp.bijectors](https://www.tensorflow.org/probability/api_docs/python/tfp/bijectors) instead.

## Classes

[`class AbsoluteValue`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/AbsoluteValue): Computes `Y = g(X) = Abs(X)`, element-wise.

[`class Affine`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Affine): Compute `Y = g(X; shift, scale) = scale @ X + shift`.

[`class AffineLinearOperator`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/AffineLinearOperator): Compute `Y = g(X; shift, scale) = scale @ X + shift`.

[`class AffineScalar`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/AffineScalar): Compute `Y = g(X; shift, scale) = scale * X + shift`.

[`class BatchNormalization`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/BatchNormalization): Compute \`Y = g(X) s.t.

[`class Bijector`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Bijector): Interface for transformations of a `Distribution` sample.

[`class Chain`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Chain): Bijector which applies a sequence of bijectors.

[`class CholeskyOuterProduct`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/CholeskyOuterProduct): Compute `g(X) = X @ X.T`; X is lower-triangular, positive-diagonal matrix.

[`class ConditionalBijector`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/ConditionalBijector): Conditional Bijector is a Bijector that allows intrinsic conditioning.

[`class Exp`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Exp): Compute `Y = g(X) = exp(X)`.

[`class FillTriangular`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/FillTriangular): Transforms vectors to triangular.

[`class Gumbel`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Gumbel): Compute `Y = g(X) = exp(-exp(-(X - loc) / scale))`.

[`class Identity`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Identity): Compute Y = g(X) = X.

[`class Inline`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Inline): Bijector constructed from custom callables.

[`class Invert`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Invert): Bijector which inverts another Bijector.

[`class Kumaraswamy`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Kumaraswamy): Compute `Y = g(X) = (1 - (1 - X)**(1 / b))**(1 / a), X in [0, 1]`.

[`class MaskedAutoregressiveFlow`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/MaskedAutoregressiveFlow): Affine MaskedAutoregressiveFlow bijector for vector-valued events.

[`class MatrixInverseTriL`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/MatrixInverseTriL): Computes `g(L) = inv(L)`, where `L` is a lower-triangular matrix.

[`class Ordered`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Ordered): Bijector which maps a tensor x_k that has increasing elements in the last

[`class Permute`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Permute): Permutes the rightmost dimension of a `Tensor`.

[`class PowerTransform`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/PowerTransform): Compute `Y = g(X) = (1 + X * c)**(1 / c), X >= -1 / c`.

[`class RealNVP`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/RealNVP): RealNVP "affine coupling layer" for vector-valued events.

[`class Reshape`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Reshape): Reshapes the `event_shape` of a `Tensor`.

[`class ScaleTriL`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/ScaleTriL): Transforms unconstrained vectors to TriL matrices with positive diagonal.

[`class Sigmoid`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Sigmoid): Bijector which computes `Y = g(X) = 1 / (1 + exp(-X))`.

[`class SinhArcsinh`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/SinhArcsinh): Compute `Y = g(X) = Sinh( (Arcsinh(X) + skewness) * tailweight )`.

[`class SoftmaxCentered`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/SoftmaxCentered): Bijector which computes `Y = g(X) = exp([X 0]) / sum(exp([X 0]))`.

[`class Softplus`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Softplus): Bijector which computes `Y = g(X) = Log[1 + exp(X)]`.

[`class Softsign`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Softsign): Bijector which computes `Y = g(X) = X / (1 + |X|)`.

[`class Square`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/Square): Compute `g(X) = X^2`; X is a positive real number.

[`class TransformDiagonal`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/TransformDiagonal): Applies a Bijector to the diagonal of a matrix.

## Functions

[`masked_autoregressive_default_template(...)`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/masked_autoregressive_default_template): Build the Masked Autoregressive Density Estimator (Germain et al., 2015). (deprecated)

[`masked_dense(...)`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/masked_dense): A autoregressively masked dense layer. (deprecated)

[`real_nvp_default_template(...)`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/distributions/bijectors/real_nvp_default_template): Build a scale-and-shift function using a multi-layer neural network. (deprecated)