class netket.experimental.models.FastGRUNet1D[source]#

Bases: FastRNN

Gated recurrent unit network with fast sampling. Only supports one previous neighbor at each site.

See netket.models.FastARNNSequential for a brief explanation of fast autoregressive sampling.

layers: int#

number of layers.

features: Union[Iterable[int], int]#

output feature density in each layer. If a single number is given, all layers except the last one will have the same number of features.

hilbert: HomogeneousHilbert#

the Hilbert space. Only homogeneous unconstrained Hilbert spaces are supported.


Computes the log wave-functions for input configurations.


inputs (Union[ndarray, Array]) – configurations with dimensions (batch, Hilbert.size).

Return type:

Union[ndarray, Array]


The log psi with dimension (batch,).