Parameters19.0M
GFLOPs32.8
Input Size640px
Best mAP46.5%
LicenseApache-2.0
Architecture
Type
one-stage
Backbone
Neural-Architecture-Search (AutoNAC)
Neck
PANet
Head
Decoupled (anchor-free, distribution focal loss)
Benchmark Results
Performance on COCO val2017 across different hardware configurations
| Hardware | Runtime | mAP@50-95 | FPS | Latency | VRAM |
|---|---|---|---|---|---|
| NVIDIA A100 | PyTorch FP32 | 46.5% | 16.6 | 60.1ms | 174 MB |
Speed Breakdown(NVIDIA A100)
4.6ms
19.2ms
36.3ms
Preprocess
Inference
Postprocess (NMS)
Usage with LibreYOLO
from libreyolo import LIBREYOLO
# Load model (auto-downloads from HuggingFace if not found locally)
model = LIBREYOLO("libreyolonass.pth")
# 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,)anchor-freenmsPaper: 47.5% mAP