Python SDK

import thrindex as thx

thx.compile(
    model: nn.Module,
    path: str | os.PathLike,
    target: str = "sim",
    dt: float = 1.0,
    overwrite: bool = True,
) -> None

import thrindex as thx
import thrindex.snn as snn

model = snn.Sequential(
    snn.Dense(700, 512),
    snn.LIF(tau_mem=20.0, threshold=0.3),
    snn.Dense(512, 20),
    snn.LIF(tau_mem=20.0, threshold=0.3),
)

thx.compile(model, "model.thx")

result = thx.run(
    path: str | os.PathLike,
    spikes: torch.Tensor | None = None,
    seed: int = 0,
) -> RunResult

@dataclass
class RunResult:
    prediction: int          # argmax of spike counts
    spike_counts: list[int]  # one per output neuron
    synaptic_ops: int        # total syn-ops
    wall_time_ms: float      # simulator wall time
    energy_pJ: float         # estimated energy

info = thx.artifact_info(path: str | os.PathLike) -> ArtifactInfo

@dataclass
class ArtifactInfo:
    format: str              # "m3"
    thrindex_version: str    # "0.2.0"
    target: str              # "sim"
    dt_ms: float             # 1.0
    crc32: str               # "d3a4f82c"
    crc32_ok: bool           # True if integrity check passes
    n_layers: int            # total layer count
    n_params: int            # total trainable parameters

thx.check(path: str | os.PathLike) -> None

thx.register_target(
    name: str,
    capability: Capability,
    backend_cls: type[Backend],
) -> None