Skip to page content
SAVRN
Search Plan a project

Open-weight model · Object detection

factory-safety-isaac-yolo

by Intelligence Big Data Processing Laboratory IBDPLab/factory-safety-isaac-yolo

factory-safety-isaac-yolo is an open-weight model for object detection from Intelligence Big Data Processing Laboratory, released under Creative Commons Attribution 4.0. Its published files total 41.1 MB.

YOLO weights for factory-safety-isaac — a body-camera-only factory safety agent built on NVIDIA Isaac Sim.

Parameters—
Context—
Weights41.1 MB
Licensecc-by-4.0
AccessOpen weights
Monthly Downloads—

Model Card

By Intelligence Big Data Processing Laboratory, published under cc-by-4.0, revision 76564c0401c7.

YOLO weights for factory-safety-isaac — a body-camera-only factory safety agent built on NVIDIA Isaac Sim. These are the two trained detection models the project uses; no other model files are hosted here (MediaPipe's hand landmarker and the Qwen2.5-7B LLM are pulled from their own upstream sources at first run, see the project README). on 7,700 synthetic images generated in Isaac Sim (Replicator auto-labeling), 70% bodycam / 30% free-viewpoint. Or with the project's own scripts (scripts/runpatrol.py --weights, scripts/runpatrol.py --pinch-weights ). Trained entirely on synthetic data (NVIDIA Isaac Sim warehouse assets + Poly Haven CC0 tool scans). See the main repository for full…

Read Intelligence Big Data Processing Laboratory's full model card

factory-safety-isaac YOLO weights

English | 한국어

YOLO weights for factory-safety-isaac — a body-camera-only factory safety agent built on NVIDIA Isaac Sim. These are the two trained detection models the project uses; no other model files are hosted here (MediaPipe's hand landmarker and the Qwen2.5-7B LLM are pulled from their own upstream sources at first run, see the project README).

Files

File Model Classes mAP50 mAP50-95 Precision Recall
warehouse_v3/best.pt YOLO26s, 960px 19 (hazard/safe states, 8 tool types, cart, worker, cone, danger sign) 0.898 0.689 0.920 0.827
pinch_v1/best.pt YOLO, 1-class lightweight pinch_point (conveyor pinch-point detector) 0.966 0.760 0.983 0.910

warehouse_v3 per-class mAP50

spill 0.920 · spill_marked 0.937 · stack_unstable 0.957 · stack_stable 0.960 · ext_fallen 0.907 · ext_blocked 0.909 · ext_ok 0.938 · worker 0.950 · cone 0.976 · danger_sign 0.950 · hammer 0.862 · screwdriver 0.828 · saw 0.806 · power_saw 0.901 · pickaxe 0.845 · shovel 0.819 · wrench 0.887 · drill 0.915 · cart 0.794

Trained on 7,700 synthetic images generated in Isaac Sim (Replicator auto-labeling), 70% bodycam / 30% free-viewpoint.

Usage

from huggingface_hub import hf_hub_download
from ultralytics import YOLO

path = hf_hub_download("IBDPLab/factory-safety-isaac-yolo", "warehouse_v3/best.pt")
model = YOLO(path)

Or with the project's own scripts (scripts/run_patrol.py --weights <path>, scripts/run_patrol.py --pinch-weights <path>).

License / provenance

Trained entirely on synthetic data (NVIDIA Isaac Sim warehouse assets + Poly Haven CC0 tool scans). See the main repository for full training/data-generation details and limitations (real-photo generalization has not been fine-tuned).

한국어

factory-safety-isaac용 YOLO 가중치입니다. factory-safety-isaac은 NVIDIA Isaac Sim 기반으로 구축한, 바디캠 영상만 사용하는 공장 안전 에이전트입니다. 이 저장소에는 프로젝트에서 사용하는 학습된 탐지 모델 2종만 올라가 있습니다. MediaPipe 손 랜드마크 모델과 Qwen2.5-7B LLM은 최초 실행 시 각 원본 출처에서 내려받습니다(프로젝트 README 참고).

파일

파일 모델 클래스 mAP50 mAP50-95 Precision Recall
warehouse_v3/best.pt YOLO26s, 960px 19개 (위험/안전 상태, 공구 8종, 카트, 작업자, 라바콘, 위험 표지판) 0.898 0.689 0.920 0.827
pinch_v1/best.pt YOLO, 단일 클래스 경량 모델 pinch_point (컨베이어 끼임 지점 탐지) 0.966 0.760 0.983 0.910
warehouse_v3 클래스별 mAP50

spill 0.920 · spill_marked 0.937 · stack_unstable 0.957 · stack_stable 0.960 · ext_fallen 0.907 · ext_blocked 0.909 · ext_ok 0.938 · worker 0.950 · cone 0.976 · danger_sign 0.950 · hammer 0.862 · screwdriver 0.828 · saw 0.806 · power_saw 0.901 · pickaxe 0.845 · shovel 0.819 · wrench 0.887 · drill 0.915 · cart 0.794

Isaac Sim에서 생성한 합성 이미지 7,700장(Replicator 자동 라벨링)으로 학습했습니다. 시점 구성은 바디캠 70%, 자유 시점 30%입니다.

사용법

from huggingface_hub import hf_hub_download
from ultralytics import YOLO

path = hf_hub_download("IBDPLab/factory-safety-isaac-yolo", "warehouse_v3/best.pt")
model = YOLO(path)

프로젝트 자체 스크립트로도 사용할 수 있습니다: scripts/run_patrol.py --weights <경로>, scripts/run_patrol.py --pinch-weights <경로>

라이선스 / 데이터 출처

전량 합성 데이터(NVIDIA Isaac Sim 창고 에셋 + Poly Haven CC0 공구 스캔)로 학습했습니다. 학습·데이터 생성 세부 사항과 한계는 메인 저장소를 참고하세요. 실사 이미지에 대한 파인튜닝은 아직 진행하지 않았으므로, 실제 환경에서의 일반화 성능은 검증되지 않았습니다.

Identity and Version

Repository
IBDPLab/factory-safety-isaac-yolo
Publisher
Intelligence Big Data Processing Laboratory
Task
Object detection
Modality
Image
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
76564c0401c7ff71be2d3e5d93ffadb239817b4f
First published
2026-10-05
Last updated
2026-10-06

Files and Weights

6 files, 41.1 MB in total. The weights are 2 files totalling 41.1 MB in pt.

Weights2 files · 41.1 MB
Configuration2 files · 638 B
Documentation1 file · 4.3 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
pinch_v1/best.ptWeights20.8 MB b9fbfa64b66f
warehouse_v3/best.ptWeights20.4 MB 40ab442f3875
pinch_v1/metrics.jsonConfiguration126 B —
warehouse_v3/metrics.jsonConfiguration512 B —
README.mdDocumentation4.3 KB —
.gitattributesRepository1.5 KB —

License and Download

License
cc-by-4.0
Access
Open weights, no gate
Download size
41.1 MB
Download from Intelligence Big Data Processing Laboratory

Released by Intelligence Big Data Processing Laboratory through its official repository on Hugging Face. Read the license.

Memory Requirements

PrecisionWeights in memory
As published41.1 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About factory-safety-isaac-yolo

Can I use factory-safety-isaac-yolo commercially?

Yes. factory-safety-isaac-yolo is released under Creative Commons Attribution 4.0. CC BY 4.0 permits sharing and adapting the work, including commercially, provided the creator is credited and changes are indicated.

Similar Models

Model · Object detection

locate-anything.cpp-gguf

Mudler

GGUF builds of nvidia/LocateAnything-3B for locate-anything.cpp - a C++/ggml inference engine for open-vocabulary detection / visual grounding, no Python at inference time. Brought to you by the LocalAI team. The detections are the same as the official PyTorch implementation (the engine is parity-gated against it), and it runs faster - on CPU and GPU. The full-precision f32 GGUF (~15 GB) is reproducible from the HF weights with scripts/convertlocateanythingtogguf.py in the repo. Same detections as the official model, faster. Full methodology, the warm/median setup, parity checks, and more images are in the repo's Slow-mode inference on the 448 fixture; vs official divides the official…

Open weights other gguf
View model

Model · Object detection

Anzhcs_YOLOs

Anzhc

YOLOs in this repo are trained with datasets that i have annotated myself, or with the help of my friends(They will be appropriately mentioned in those cases). YOLOs on open datasets will have their own pages. Ultralytics 8.3.217 updates mask handling, which breaks function in main Adetailer repo. Install Ultralytics==8.3.216 or lower. Alternatively - use forks that fix this. - Fixed in main repo. I've added some features to make Adetailer more usable and less manual - https://github.com/Anzhc/aadetailer-reforge Im open to commissions, hit me up in Discord - anzhc P.S. All model names in tables have download links attached:3 Series of models aiming at detecting and segmenting face…

Open weights agpl-3.0 ultralytics
View model

This is a fine-tuned version of YOLOv11 (n, s, m, l, x) specialized for License Plate Detection, using a public dataset from Roboflow Universe: The upstream Roboflow dataset (license-plate-recognition-rxg4e) contains train/test contamination — the same source images appear in both the training and test splits with only minor manual augmentation applied (see Discussion #2 for concrete examples). As a result: - The reported metrics below are likely overestimated, because the test set is not a true held-out evaluation. - Real-world generalization performance is expected to be lower than the numbers in the table. - Treat all evaluation figures with caution and validate the model on your own…

Open weights agpl-3.0 ultralytics
View model

Model · Object detection

surya_layout2

Datalab

A lightweight document layout detection model used by Surya. It detects layout regions (text, tables, figures, headers, captions, equations, etc.) on a page image and runs on CPU or GPU. This is the "fast" layout detector — a compact object detector that serves as a drop-in alternative to Surya's VLM-based layout model. Documentation, installation, and everything else lives in the Point the fast layout predictor at this checkpoint: Or make it the default so the CLI and library use it without an explicit path: Released under the AI Pubs OpenRAIL-M license (see LICENSE) — the same license as the surya-ocr-2 model weights.

Open weights openrail surya
View model

Model · Object detection

detr-resnet-50

Joshua

https://huggingface.co/facebook/detr-resnet-50 with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Test it out here, or create your own object-detection demo with 1 click! Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Open weights 1,024 tokens transformers.js
View model