Back to Leaderboard
Parameters
76.0M
FLOPs
259.0G
Input Size
640px
License
Apache-2.0
Architecture
Type
transformer
Backbone
ResNet-101
Neck
HybridEncoder
Head
DETR
Benchmark Results
Performance on COCO val2017 across different hardware configurations
| Hardware | mAP@50-95 | FPS | Latency | VRAM |
|---|---|---|---|---|
| NVIDIA A100 (TensorRT FP16) | 54.3% | 58.6 | 17.1ms | 3221 MB |
| NVIDIA T4 (TensorRT FP16) | 54.2% | 21.3 | 46.9ms | 3289 MB |
| CPU (ONNX Runtime) | 54.3% | 2.6 | 385.4ms | 3250 MB |
Speed Breakdown (A100 TensorRT)
End-to-end latency breakdown showing preprocessing, inference, and postprocessing times
1.0ms
13.4ms
2.7ms
Preprocess
Inference
Postprocess (NMS)
Usage with LibreYOLO
from libreyolo import YOLO
# Load model
model = YOLO.from_pretrained("https://huggingface.co/Libre-YOLO/rtdetr-r101")
# Run inference
results = model.predict("image.jpg")
# Process results
for box in results.boxes:
print(f"Class: {box.cls}, Confidence: {box.conf:.2f}")transformerno-nmshighest-accuracy
Related Models (rtdetr)