Back to Leaderboard

YOLOv7-X

yolov7

one-stage detector with E-ELAN backbone

Parameters

71.3M

FLOPs

189.9G

Input Size

640px

License

GPL-3.0

Architecture

Type

one-stage

Backbone

E-ELAN

Neck

SPPCSPC

Head

RepConv

Benchmark Results
Performance on COCO val2017 across different hardware configurations
HardwaremAP@50-95FPSLatencyVRAM
NVIDIA A100 (TensorRT FP16)53.2%66.515.0ms2940 MB
NVIDIA T4 (TensorRT FP16)53.0%24.940.1ms2942 MB
CPU (ONNX Runtime)53.0%2.9339.6ms2947 MB
Speed Breakdown (A100 TensorRT)
End-to-end latency breakdown showing preprocessing, inference, and postprocessing times
1.1ms
11.3ms
2.7ms
Preprocess
Inference
Postprocess (NMS)
Usage with LibreYOLO
from libreyolo import YOLO

# Load model
model = YOLO.from_pretrained("https://huggingface.co/Libre-YOLO/yolov7-x")

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

# Process results
for box in results.boxes:
    print(f"Class: {box.cls}, Confidence: {box.conf:.2f}")
high-accuracy
Related Models (yolov7)