factory-safety-isaac YOLO weights

English | ํ•œ๊ตญ์–ด

YOLO weights for factory-safety-isaac โ€” 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 ยท spill_marked 0.937 ยท stack_unstable 0.957 ยท stack_stable 0.960 ยท ext_fallen 0.907 ยท ext_blocked 0.909 ยท ext_ok 0.938 ยท worker 0.950 ยท cone 0.976 ยท danger_sign 0.950 ยท hammer 0.862 ยท screwdriver 0.828 ยท saw 0.806 ยท power_saw 0.901 ยท pickaxe 0.845 ยท shovel 0.819 ยท wrench 0.887 ยท drill 0.915 ยท 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).


ํ•œ๊ตญ์–ด

factory-safety-isaac์šฉ YOLO ๊ฐ€์ค‘์น˜์ž…๋‹ˆ๋‹ค. factory-safety-isaac์€ NVIDIA Isaac Sim ๊ธฐ๋ฐ˜์œผ๋กœ ๊ตฌ์ถ•ํ•œ, ๋ฐ”๋””์บ  ์˜์ƒ๋งŒ ์‚ฌ์šฉํ•˜๋Š” ๊ณต์žฅ ์•ˆ์ „ ์—์ด์ „ํŠธ์ž…๋‹ˆ๋‹ค. ์ด ์ €์žฅ์†Œ์—๋Š” ํ”„๋กœ์ ํŠธ์—์„œ ์‚ฌ์šฉํ•˜๋Š” ํ•™์Šต๋œ ํƒ์ง€ ๋ชจ๋ธ 2์ข…๋งŒ ์˜ฌ๋ผ๊ฐ€ ์žˆ์Šต๋‹ˆ๋‹ค. MediaPipe ์† ๋žœ๋“œ๋งˆํฌ ๋ชจ๋ธ๊ณผ Qwen2.5-7B LLM์€ ์ตœ์ดˆ ์‹คํ–‰ ์‹œ ๊ฐ ์›๋ณธ ์ถœ์ฒ˜์—์„œ ๋‚ด๋ ค๋ฐ›์Šต๋‹ˆ๋‹ค(ํ”„๋กœ์ ํŠธ README ์ฐธ๊ณ ).

ํŒŒ์ผ

ํŒŒ์ผ ๋ชจ๋ธ ํด๋ž˜์Šค mAP50 mAP50-95 Precision Recall
warehouse_v3/best.pt YOLO26s, 960px 19๊ฐœ (์œ„ํ—˜/์•ˆ์ „ ์ƒํƒœ, ๊ณต๊ตฌ 8์ข…, ์นดํŠธ, ์ž‘์—…์ž, ๋ผ๋ฐ”์ฝ˜, ์œ„ํ—˜ ํ‘œ์ง€ํŒ) 0.898 0.689 0.920 0.827
pinch_v1/best.pt YOLO, ๋‹จ์ผ ํด๋ž˜์Šค ๊ฒฝ๋Ÿ‰ ๋ชจ๋ธ pinch_point (์ปจ๋ฒ ์ด์–ด ๋ผ์ž„ ์ง€์  ํƒ์ง€) 0.966 0.760 0.983 0.910

warehouse_v3 ํด๋ž˜์Šค๋ณ„ mAP50

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

Isaac Sim์—์„œ ์ƒ์„ฑํ•œ ํ•ฉ์„ฑ ์ด๋ฏธ์ง€ 7,700์žฅ(Replicator ์ž๋™ ๋ผ๋ฒจ๋ง)์œผ๋กœ ํ•™์Šตํ–ˆ์Šต๋‹ˆ๋‹ค. ์‹œ์  ๊ตฌ์„ฑ์€ ๋ฐ”๋””์บ  70%, ์ž์œ  ์‹œ์  30%์ž…๋‹ˆ๋‹ค.

์‚ฌ์šฉ๋ฒ•

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)

ํ”„๋กœ์ ํŠธ ์ž์ฒด ์Šคํฌ๋ฆฝํŠธ๋กœ๋„ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค: scripts/run_patrol.py --weights <๊ฒฝ๋กœ>, scripts/run_patrol.py --pinch-weights <๊ฒฝ๋กœ>

๋ผ์ด์„ ์Šค / ๋ฐ์ดํ„ฐ ์ถœ์ฒ˜

์ „๋Ÿ‰ ํ•ฉ์„ฑ ๋ฐ์ดํ„ฐ(NVIDIA Isaac Sim ์ฐฝ๊ณ  ์—์…‹ + Poly Haven CC0 ๊ณต๊ตฌ ์Šค์บ”)๋กœ ํ•™์Šตํ–ˆ์Šต๋‹ˆ๋‹ค. ํ•™์Šตยท๋ฐ์ดํ„ฐ ์ƒ์„ฑ ์„ธ๋ถ€ ์‚ฌํ•ญ๊ณผ ํ•œ๊ณ„๋Š” ๋ฉ”์ธ ์ €์žฅ์†Œ๋ฅผ ์ฐธ๊ณ ํ•˜์„ธ์š”. ์‹ค์‚ฌ ์ด๋ฏธ์ง€์— ๋Œ€ํ•œ ํŒŒ์ธํŠœ๋‹์€ ์•„์ง ์ง„ํ–‰ํ•˜์ง€ ์•Š์•˜์œผ๋ฏ€๋กœ, ์‹ค์ œ ํ™˜๊ฒฝ์—์„œ์˜ ์ผ๋ฐ˜ํ™” ์„ฑ๋Šฅ์€ ๊ฒ€์ฆ๋˜์ง€ ์•Š์•˜์Šต๋‹ˆ๋‹ค.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support