zuko.transforms#
Parameterizable transformations.
Classes#
Creates a transformation \(f(x) = f_n \circ \dots \circ f_0(x)\). |
|
Creates a transformation \(f(x) = x\). |
|
Creates a transformation \(f(x) = -\cos(x)\). |
|
Creates a transformation \(f(x) = \sin(x)\). |
|
Creates a transformation that maps \(\mathbb{R}\) to the interval \([-B, B]\). |
|
Creates a transformation that circularly shifts the interval \([-B, B]\). |
|
Creates a transformation \(f(x) = \alpha x + \beta\). |
|
Creates a monotonic rational-quadratic spline (RQS) transformation. |
|
Creates a transformation from a monotonic univariate function \(f_\phi(x)\). |
|
Creates a monotonic transformation \(f(x)\) by integrating a positive univariate function \(g(x)\). |
|
Creates a sum-of-squares (SOS) polynomial transformation. |
|
Creates a free-form Jacobian transformation. |
|
Transform via an autoregressive scheme. |
|
Creates a transformation that permutes the elements. |
Descriptions#
- class zuko.transforms.ComposedTransform(*transforms, **kwargs)#
Creates a transformation \(f(x) = f_n \circ \dots \circ f_0(x)\).
- Parameters
transforms (Transform) – A sequence of transformations \(f_i\).
- class zuko.transforms.IdentityTransform(cache_size=0)#
Creates a transformation \(f(x) = x\).
- class zuko.transforms.CosTransform(cache_size=0)#
Creates a transformation \(f(x) = -\cos(x)\).
- class zuko.transforms.SinTransform(cache_size=0)#
Creates a transformation \(f(x) = \sin(x)\).
- class zuko.transforms.SoftclipTransform(bound=5.0, **kwargs)#
Creates a transformation that maps \(\mathbb{R}\) to the interval \([-B, B]\).
\[f(x) = \frac{x}{1 + \left| \frac{x}{B} \right|}\]- Parameters
bound (float) – The codomain bound \(B\).
- class zuko.transforms.CircularShiftTransform(bound=5.0, **kwargs)#
Creates a transformation that circularly shifts the interval \([-B, B]\).
\[f(x) = (x \bmod 2B) - B\]Note
This transformation is only bijective over its domain \([-B, B]\) as \(f(x) = f(x + 2kB)\) for all \(k \in \mathbb{Z}\).
- Parameters
bound (float) – The domain bound \(B\).
- class zuko.transforms.MonotonicAffineTransform(shift, scale, slope=0.001, **kwargs)#
Creates a transformation \(f(x) = \alpha x + \beta\).
- class zuko.transforms.MonotonicRQSTransform(widths, heights, derivatives, bound=5.0, slope=0.001, **kwargs)#
Creates a monotonic rational-quadratic spline (RQS) transformation.
References
Neural Spline Flows (Durkan et al., 2019)- Parameters
widths (Tensor) – The unconstrained bin widths, with shape \((*, K)\).
heights (Tensor) – The unconstrained bin heights, with shape \((*, K)\).
derivatives (Tensor) – The unconstrained knot derivatives, with shape \((*, K - 1)\).
bound (float) – The spline’s (co)domain bound \(B\).
slope (float) – The minimum slope of the transformation.
- class zuko.transforms.MonotonicTransform(f, phi=(), bound=5.0, eps=1e-06, **kwargs)#
Creates a transformation from a monotonic univariate function \(f_\phi(x)\).
The inverse function \(f_\phi^{-1}\) is approximated using the bisection method.
- class zuko.transforms.UnconstrainedMonotonicTransform(g, C, n=16, **kwargs)#
Creates a monotonic transformation \(f(x)\) by integrating a positive univariate function \(g(x)\).
\[f(x) = \int_0^x g(u) ~ du + C\]The definite integral is estimated by a \(n\)-point Gauss-Legendre quadrature.
- class zuko.transforms.SOSPolynomialTransform(a, C, **kwargs)#
Creates a sum-of-squares (SOS) polynomial transformation.
The transformation \(f(x)\) is expressed as the primitive integral of the sum of \(K\) squared polynomials of degree \(L\).
\[f(x) = \int_0^x \sum_{i = 1}^K \left( 1 + \sum_{j = 0}^L a_{i,j} ~ u^j \right)^2 ~ du + C\]References
Sum-of-Squares Polynomial Flow (Jaini et al., 2019)- Parameters
a (Tensor) – The polynomial coefficients \(a\), with shape \((*, K, L + 1)\).
C (Tensor) – The integration constant \(C\).
kwargs – Keyword arguments passed to
UnconstrainedMonotonicTransform.
- class zuko.transforms.FreeFormJacobianTransform(f, time, phi=(), exact=True, **kwargs)#
Creates a free-form Jacobian transformation.
The transformation is the integration of a system of first-order ordinary differential equations
\[x(T) = \int_0^T f_\phi(t, x(t)) ~ dt .\]References
FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models (Grathwohl et al., 2018)- Parameters
f (Callable[[Tensor, Tensor], Tensor]) – A system of first-order ODEs \(f_\phi\).
time (Tensor) – The integration time \(T\).
phi (Iterable[Tensor]) – The parameters \(\phi\) of \(f_\phi\).
exact (bool) – Whether the exact log-determinant of the Jacobian or an unbiased stochastic estimate thereof is calculated.
- class zuko.transforms.AutoregressiveTransform(meta, passes, **kwargs)#
Transform via an autoregressive scheme.
\[y_i = f(x_i; x_{<i})\]
- class zuko.transforms.PermutationTransform(order, **kwargs)#
Creates a transformation that permutes the elements.
- Parameters
order (LongTensor) – The permutation order, with shape \((*, D)\).