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.
- Attributes
-
layers: int
number of layers.
-
features: 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.
- Methods
-
__call__(inputs)[source]
Computes the log wave-functions for input configurations.
- Parameters:
inputs (Union[ndarray, Array]) – configurations with dimensions (batch, Hilbert.size).
- Return type:
Union[ndarray, Array]
- Returns:
The log psi with dimension (batch,).
