IMLCV.implementations.CV

`IMLCV.implementations.CV`#

Module Contents#

Classes#

`RealNVP`	use in combination with swaplink
`DistraxRealNVP`	creates bijective CV function based on a distrax flow. The seup function should initialize the bijector
`MetricUMAP`	class to keep track of topology of given CV. Identifies the periodicitie of CVs and maps to unit square with correct peridicities
`hyperTorus`	class to keep track of topology of given CV. Identifies the periodicitie of CVs and maps to unit square with correct peridicities

Functions#

`Volume`(sp, _)
`distance_descriptor`()
`dihedral`(numbers)	from https://stackoverflow.com/questions/20305272/dihedral-torsion-
`sb_descriptor`(r_cut, n_max, l_max[, references, ...])
`NoneCV`(→ IMLCV.base.CV.CollectiveVariable)
`rotate_2d`(alpha)
`project_distances`(a)
`scale_cv_trans`(array)	axis 0 is batch axis
`trunc_svd`(→ tuple[IMLCV.base.CV.CV, IMLCV.base.CV.CvTrans])
`get_sinkhorn_divergence`(nli, pi[, sort, alpha_rematch])
`un_atomize`(x, nl, _)

IMLCV.implementations.CV.Volume(sp: IMLCV.base.CV.SystemParams, _)[source]#

IMLCV.implementations.CV.distance_descriptor()[source]#

IMLCV.implementations.CV.dihedral(numbers: list[int] | Array)[source]#

from https://stackoverflow.com/questions/20305272/dihedral-torsion- angle-from-four-points-in-cartesian- coordinates-in-python.

Parameters:: numbers – list with index of 4 atoms that form dihedral

IMLCV.implementations.CV.sb_descriptor(r_cut, n_max: int, l_max: int, references: SystemParams | None = None, references_nl: NeighbourList | None = None, reduce=True, reshape=False)[source]#

IMLCV.implementations.CV.NoneCV() → IMLCV.base.CV.CollectiveVariable[source]#

IMLCV.implementations.CV.rotate_2d(alpha)[source]#

IMLCV.implementations.CV.project_distances(a)[source]#

IMLCV.implementations.CV.scale_cv_trans(array: IMLCV.base.CV.CV)[source]#: axis 0 is batch axis

IMLCV.implementations.CV.trunc_svd(m: IMLCV.base.CV.CV) → tuple[IMLCV.base.CV.CV, IMLCV.base.CV.CvTrans][source]#

IMLCV.implementations.CV.get_sinkhorn_divergence(nli: NeighbourList | None, pi: Array | None, sort='rematch', alpha_rematch=0.1)[source]#

IMLCV.implementations.CV.un_atomize(x: IMLCV.base.CV.CV, nl, _)[source]#

class IMLCV.implementations.CV.RealNVP[source]#

Bases: IMLCV.base.CV.CvFunNn

use in combination with swaplink

_: dataclasses.KW_ONLY[source]#

features: int[source]#

cv_input: IMLCV.base.CV.CvFunInput[source]#

setup() → None[source]#

Initializes a Module lazily (similar to a lazy __init__).

setup is called once lazily on a module instance when a module is bound, immediately before any other methods like __call__ are invoked, or before a setup-defined attribute on self is accessed.

This can happen in three cases:

Immediately when invoking apply(), init() or init_and_output().
Once the module is given a name by being assigned to an attribute of another module inside the other module’s setup method (see __setattr__()):
class MyModule(nn.Module):
  def setup(self):
    submodule = Conv(...)

    # Accessing `submodule` attributes does not yet work here.

    # The following line invokes `self.__setattr__`, which gives
    # `submodule` the name "conv1".
    self.conv1 = submodule

    # Accessing `submodule` attributes or methods is now safe and
    # either causes setup() to be called once.
Once a module is constructed inside a method wrapped with compact(), immediately before another method is called or setup defined attribute is accessed.

forward(x: IMLCV.base.CV.CV, nl: NeighbourList | None, conditioners: list[CV] | None = None)[source]#

backward(z: IMLCV.base.CV.CV, nl: NeighbourList | None, conditioners: list[CV] | None = None)[source]#

class IMLCV.implementations.CV.DistraxRealNVP[source]#

Bases: IMLCV.base.CV.CvFunDistrax

creates bijective CV function based on a distrax flow. The seup function should initialize the bijector

class RealNVP(CvFunDistrax):

_: dataclasses.KW_ONLY latent_dim: int

def setup(self):

self.s = Dense(features=self.latent_dim) self.t = Dense(features=self.latent_dim)

# Alternating binary mask. self.bijector = distrax.as_bijector(

tfp.bijectors.RealNVP(
fraction_masked=0.5, shift_and_log_scale_fn=self.shift_and_scale,

)

)

def shift_and_scale(self, x0, input_depth, **condition_kwargs):

return self.s(x0), self.t(x0)

_: dataclasses.KW_ONLY[source]#

latent_dim: int[source]#

setup()[source]#: Creates the flow model.

shift_and_scale(x0, input_depth, **condition_kwargs)[source]#

class IMLCV.implementations.CV.MetricUMAP(periodicities, bounding_box=None)[source]#

Bases: IMLCV.base.CV.CvMetric

class to keep track of topology of given CV. Identifies the periodicitie of CVs and maps to unit square with correct peridicities

class IMLCV.implementations.CV.hyperTorus(n)[source]#