Back to Leaderboard
Parameters
7.2M
FLOPs
13.5G
Input Size
640px
License
MIT
Architecture
Type
one-stage
Backbone
GELAN
Neck
PGI
Head
Decoupled
Benchmark Results
Performance on COCO val2017 across different hardware configurations
| Hardware | Runtime | mAP@50-95 | FPS | Latency | VRAM |
|---|---|---|---|---|---|
| NVIDIA A100 | PyTorch FP32 | 38.3% | 28.0 | 35.7ms | — |
| Raspberry Pi 5 | PyTorch FP32 | 45.4% | 1.3 | 744.8ms | — |
Speed Breakdown(Raspberry Pi 5)
End-to-end latency breakdown showing preprocessing, inference, and postprocessing times
2.9ms
734.9ms
4.0ms
Preprocess
Inference
Postprocess (NMS)
Usage with LibreYOLO
from libreyolo import LIBREYOLO
# Load model (auto-downloads from HuggingFace if not found locally)
model = LIBREYOLO("libreyolo9s.pt")
# Run inference
result = model("image.jpg", conf=0.25, iou=0.45)
# Process results
print(f"Found {len(result)} objects")
print(result.boxes.xyxy) # bounding boxes (N, 4)
print(result.boxes.conf) # confidence scores (N,)
print(result.boxes.cls) # class IDs (N,)balanced