IMLCV.implementations.tensorflow.CvDiscovery

IMLCV.implementations.tensorflow.CvDiscovery#

Classes#

hkFunBase

Helper class that provides a standard way to create an ABC using

TranformerUMAP

Base class for dataclasses that should act like a JAX pytree node.

Functions#

umap_function(x, nl, c, enc)

umap_encoder(x, nlayers, nunits, outdim)

Module Contents#

IMLCV.implementations.tensorflow.CvDiscovery.umap_function(x: IMLCV.base.CV.CV, nl: IMLCV.base.CV.NeighbourList, c, enc)#
IMLCV.implementations.tensorflow.CvDiscovery.umap_encoder(x, nlayers, nunits, outdim)#
class IMLCV.implementations.tensorflow.CvDiscovery.hkFunBase(*args, **kwargs)#

Bases: IMLCV.base.CV.CvFunBase

Helper class that provides a standard way to create an ABC using inheritance.

_: dataclasses.KW_ONLY#
fwd_params: dict#
fwd_kwargs: dict#
bwd_params: dict | None#
bwd_kwargs: dict | None#
_calc(x: IMLCV.base.CV.CV, nl: IMLCV.base.CV.NeighbourList, reverse=False, conditioners: list[IMLCV.base.CV.CV] | None = None, shmap=False) → IMLCV.base.CV.CV#
class IMLCV.implementations.tensorflow.CvDiscovery.TranformerUMAP(*args, **kwargs)#

Bases: IMLCV.base.CVDiscovery.Transformer

Base class for dataclasses that should act like a JAX pytree node.

decoder: bool = False#
nunits: int = 256#
nlayers: int = 3#
parametric: bool = True#
densmap: bool = False#
n_neighbors: int = 20#
_fit(x: list[IMLCV.base.CV.CV], x_t: list[IMLCV.base.CV.CV] | None, w: list[jax.Array], dlo: IMLCV.base.rounds.DataLoaderOutput, decoder=False, nunits=256, nlayers=3, parametric=True, densmap=False, n_neighbors=20, chunk_size=None, verbose=True, macro_chunk=1000, **kwargs)#
Contents