Parameters16.3M
GFLOPs37.8
Input Size640px
Best mAP45.9%
LicenseApache-2.0
Architecture
Type
one-stage
Backbone
TinyNAS
Neck
GiraffeNeck
Head
ZeroHead
Benchmark Results
Performance on COCO val2017 across different hardware configurations
| Hardware | Runtime | mAP@50-95 | FPS | Latency | VRAM |
|---|---|---|---|---|---|
| NVIDIA RTX 5070 Ti | PyTorch FP32 | 45.9% | 8.4 | 118.6ms | 129 MB |
Speed Breakdown(NVIDIA RTX 5070 Ti)
2.3ms
8.4ms
107.8ms
Preprocess
Inference
Postprocess (NMS)
Usage with LibreYOLO
from libreyolo import LIBREYOLO
# Load model (auto-downloads from HuggingFace if not found locally)
model = LIBREYOLO("libredamoyolos.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: 46% mAP