AGENT SKILL

encoding-training

Route spike encoding, surrogate gradients, training helpers, losses, monitors, quantization, STDP, and backprop-wrapper questions.

License 许可
MIT
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
encoding-training
license
MIT
metadata
{ "disco-role": "operating" }
description
Route spike encoding, surrogate gradients, training helpers, losses, monitors, quantization, STDP, and backprop-wrapper questions.
disable-model-invocation
true

02 资源文件 7

03 SKILL.md 正文

encoding-training

Use this sub-skill for workflows that start with raw tensors or labels and end with spike-coded data, a training step, or output/gradient inspection.

Ask this sub-skill about

  • spikegen encodings: rate, latency, delta, and target coding
  • surrogate gradients for neuron spike_grad
  • loss and accuracy helpers in snntorch.functional
  • utils.reset, data_subset, and valid_split
  • backprop wrappers: BPTT, TBPTT, RTRL
  • monitors for spikes, inputs, attributes, and gradients
  • functional.quant.state_quant
  • functional.stdp_learner.STDPLearner

Route elsewhere

  • neuron definitions and reset semantics in detail -> core-neurons
  • NIR export/import -> nir-interoperability
  • raster plots, animations, and spike histograms -> plotting
  • legacy spikevision datasets -> spikevision

Start here

  1. references/workflows.md
  2. references/api-reference.md
  3. references/troubleshooting.md

Bundled smoke helpers

  • scripts/spike_encoding_smoke.py
  • scripts/synthetic_bptt_smoke.py
  • scripts/shape_mismatch_diagnostic.py
  • scripts/stdp_smoke.py

Import reminders

  • Use import snntorch.functional as SF for accuracy, losses, regularization, and probes.
  • Import quantization and STDP helpers from their submodules: from snntorch.functional import quant from snntorch.functional.stdp_learner import STDPLearner
  • There is no standalone SF.metrics namespace in this release; use SF.accuracy_rate and SF.accuracy_temporal.
  • backprop is a compatibility layer and emits a deprecation warning.
  • Call utils.reset(net) between sequences unless a wrapper already does it.
  • STDPLearner.reset() is not reliable in this release; create a fresh learner when you need a clean STDP episode.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351