Back to Leaderboard

RT-DETR-R101

rtdetr

transformer detector with ResNet-101 backbone

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
HardwaremAP@50-95FPSLatencyVRAM
NVIDIA A100 (TensorRT FP16)54.3%58.617.1ms3221 MB
NVIDIA T4 (TensorRT FP16)54.2%21.346.9ms3289 MB
CPU (ONNX Runtime)54.3%2.6385.4ms3250 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