Back to Leaderboard
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
| Hardware | mAP@50-95 | FPS | Latency | VRAM |
|---|---|---|---|---|
| NVIDIA A100 (TensorRT FP16) | 53.2% | 66.5 | 15.0ms | 2940 MB |
| NVIDIA T4 (TensorRT FP16) | 53.0% | 24.9 | 40.1ms | 2942 MB |
| CPU (ONNX Runtime) | 53.0% | 2.9 | 339.6ms | 2947 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)