Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

ONNX importer: LSTM, Gather, Unsqueeze/Squeeze, Cast, Where, If (Silero VAD import as the gate)

Open
  • Is something wrong?
#1,279 1 comment 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
25/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Active
Tech stack
kotlin
Domain
machine-learning

Research direction

Start with OnnxImport.kt and the existing converters, then read the Lstm API from #823 and the ONNX opset semantics described here. The work spans recurrent lowering, multiple operators, constant-folded control flow, and test coverage; run the one-node converter tests and the pinned silero_vad.onnx import against its ORT golden. Done means end-to-end import without hand edits and outputs within 1e-4.

Written by the indexing model from the issue text.

Description

enhancement file-format:onnx

Context

skainet-io-onnx's graph importer (OnnxImport.kt) handles Add, BatchNormalization, Concat, Conv, Div, Gemm, LeakyRelu, MatMul, MaxPool, Mul, Relu, Reshape, Resize, Sigmoid, Silu, Slice, Softmax, Split, Sub, Transpose, Upsample — the YOLO-shaped set from #230. Recurrent and control-flow nodes are absent, so common small audio/speech graphs (Silero VAD, RNN-T prediction nets, NeMo exports) cannot be imported even though the DSL has Lstm (#823) and gather.

This is the verification path for the native Silero VAD issue: importing the upstream graph and comparing against the hand-written module catches drift in either.

Scope

  • LSTM (ONNX opset ≥ 7 semantics: W, R, B layouts, initial_h/initial_c, direction=forward first; bidirectional as a follow-up) lowered onto Lstm.step unrolled over the sequence axis.
  • Gather, Unsqueeze, Squeeze, Cast, Where, Shape/ConstantOfShape as needed by the Silero graph.
  • If with constant-foldable conditions (Silero's sample-rate branch) — fold at import when the condition is an initializer, reject otherwise with a clear message rather than silently importing one branch.
  • Import test on the pinned silero_vad.onnx: graph builds, forward matches ORT golden within 1e-4 (same golden as the native Silero issue).
  • Ground-truth coverage for the new ops (#985).

Acceptance

  • OnnxLoader imports Silero VAD end to end without hand edits to the file.
  • Each new converter has a unit test with a minimal one-node graph.

Related

  • #230 — ONNX I/O module MVP
  • #823 — Lstm
  • #985 — ground-truth op coverage
Dominant language
Kotlin
Stars
52
Forks
15
Avg merge
1d 15h
Merged PRs (30d)
36

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from SKaiNET-developers/SKaiNET

All issues in SKaiNET-developers/SKaiNET

Similar issues

More Kotlin issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.