Quickstart

pip install thrindex

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")

thrindex run model.thx

═══════════════════════════════════════════════════════
 thrindex 0.3.0  |  target: sim  |  seed: 0
═══════════════════════════════════════════════════════
 model:  Dense(700→512) → LIF(τ=20ms) → Dense(512→20) → LIF(τ=20ms)
 input:  100 timesteps × 700 features
───────────────────────────────────────────────────────
 prediction:  class 7  —  rate score 0.312
───────────────────────────────────────────────────────
 output spike rate:   3.1%
 synaptic ops:        16640
 modeled energy:      8.32 nJ  (coefficient: 0.5 pJ/syn-op)
 sim wall time:       0.015s
═══════════════════════════════════════════════════════