Back to Leaderboard

YOLOX-L

yolox

one-stage detector with CSPDarknet backbone

Parameters

54.2M

FLOPs

155.6G

Input Size

640px

License

Apache-2.0

Architecture

Type

one-stage

Backbone

CSPDarknet

Neck

PAFPN

Head

Decoupled

Benchmark Results
Performance on COCO val2017 across different hardware configurations
HardwaremAP@50-95FPSLatencyVRAM
NVIDIA A100 (TensorRT FP16)49.6%77.013.0ms2375 MB
NVIDIA T4 (TensorRT FP16)49.8%29.034.5ms2391 MB
CPU (ONNX Runtime)49.6%3.4298.1ms2229 MB
Speed Breakdown (A100 TensorRT)
End-to-end latency breakdown showing preprocessing, inference, and postprocessing times
1.1ms
9.3ms
2.6ms
Preprocess
Inference
Postprocess (NMS)
Usage with LibreYOLO
from libreyolo import YOLO

# Load model
model = YOLO.from_pretrained("https://huggingface.co/Libre-YOLO/yolox-l")

# Run inference
results = model.predict("image.jpg")

# Process results
for box in results.boxes:
    print(f"Class: {box.cls}, Confidence: {box.conf:.2f}")
high-accuracymegvii