Detection: faces and objects
Collection
YuNet (OpenCV Zoo, dynamic input) and Megvii's official YOLOX ONNX (nano / s). • 3 items • Updated
YOLOX-s (COCO object detection, 640px)
Browser-ready import artifacts for object-detection, produced by SkillSafe's
reproducible converter (models/ in skillsafe.ai)
from a pinned upstream source. Every byte here is derivable from that source plus
the recipe below; nothing was edited by hand.
Provenance
| Upstream | https://github.com/Megvii-BaseDetection/YOLOX/releases/download/0.1.1rc0/yolox_s.onnx |
| Upstream SHA-256 / commit | 0.1.1rc0 |
| Recipe | recipes/yolox-s.yaml — sha256 517fe6aaa4b7227358e16a2d3cba2d366c44c2abf5b62a4af14aeedd40899cb4 |
| Toolchain | Python 3.12.13, torch 2.10.0, onnx 1.23.0, onnxruntime 1.30.0 on Darwin 25.6.0 arm64 |
| Converted | 2026-09-22T18:56:09+00:00 |
Files
| file | class | size | SHA-256 |
|---|---|---|---|
yolox_s.onnx |
registry | 34.20 MB | c5c2d13e59ae883e6af3b45daea64af4833a4951c92d116ec270d9ddbe998063 |
registry files are parameter files served from models.skillsafe.ai once vetted;
bundle files ship inside an app; registry-shared is a runtime library reused by
every model of the same architecture.
Verification
Imported as published upstream (no conversion). Each file is pinned by SHA-256 to its source; every ONNX file passed onnx.checker and a CPU smoke run under onnxruntime with zero-filled inputs at the declared shapes:
| file | inputs | outputs | ms |
|---|---|---|---|
yolox_s.onnx |
images[1, 3, 640, 640] | output[1, 8400, 85] | 57.8 |
Use in the browser
import * as ort from "onnxruntime-web";
const session = await ort.InferenceSession.create("https://huggingface.co/skillsafe-ai/yolox-s/resolve/main/yolox_s.onnx", { executionProviders: ["webgpu", "wasm"] });
Contract (yolox_s.onnx): input images float32 [1, 3, 640, 640] → output output float32 [1, 8400, 85]. Opset 11.
Licence and attribution
YOLOX: Copyright (c) 2021-2022 Megvii Inc. Apache License 2.0. https://github.com/Megvii-BaseDetection/YOLOX
Licence: Apache-2.0 — notice: https://github.com/Megvii-BaseDetection/YOLOX/blob/main/LICENSE. The conversion recipe and this model card are part of the SkillSafe repository and carry its licence; the weights remain under the upstream licence above.
The full manifest.json in this repo records the recipe, sources, toolchain
(including the uv.lock hash) and per-file verification numbers.