Renesas/YOLOv11-ONNX

YOLOv11 (ONNX) – Renesas X5H

Introduction

This repository hosts YOLOv11, targeting the Renesas R-Car X5H platform for object detection inference on the NPX6 NPU.

Note on size variant: The upstream benchmark export identifies this model only as "Yolov11", without a size suffix. The compile-artifact filename recorded alongside the benchmark run (yolo11l_quantization_config.json) confirms this is the YOLO11-L (Large) variant, not an unspecified or averaged size — this repo documents that specific variant.

• Model Architecture: YOLO11 — Ultralytics' 2024 real-time object detection architecture (C3k2 blocks, C2PSA attention module), Large (L) size
• Source Model: Ultralytics/YOLO11 — checkpoint yolo11l.pt
• Task: Object Detection (COCO, 80 classes)
• Parameters: 25.3M (published Ultralytics YOLO11 docs table, YOLO11l @ 640px, 86.9 GFLOPs)
• License note: Ultralytics YOLO11 is distributed under AGPL-3.0 (or a commercial Ultralytics Enterprise license) — this differs from the Apache-2.0 default used by most other repos in this collection.

Deployment Flow

The FP32 ONNX model is auto-cast to INT8 by the Renesas MWMX toolchain at compile time — no separate quantization step is required.

yolo11l_..._optimized.onnx (FP32)
        │
        └─▶  MWMX Runtime  ──▶  INT8 auto-cast  ──▶  NPX6 NPU

Provided Artifacts

Artifact	Status	Notes
FP32 (ONNX)	✅	fp32/yolo11l.onnx — FP32 ONNX export

Performance

Measured on Renesas R-Car X5H via the MWMX runtime (APM50 ship-performance CI pipeline).

Benchmark configuration: Single NPU · Single AI Core · Batch size: 1 · Input: 3 × 640 × 640

Runtime	Precision	Device	Latency (ms)	Type
MWMX Runtime	INT8 (auto)	X5H · 1× NPU · 1 Core · 850 MHz	36.256304	Measured

Only the 1-AI-core slice was run for this model in the source benchmark export — the 12-core slice was skipped, so no 12-core row is reported here.

Accuracy

TBD — not yet measured/published for this repo.

---

Runtime Details

MWMX Runtime

• Engine: Renesas MWMX (Middleware MX) native inference runtime
• Input format: FP32 ONNX (compiled by the MWMX toolchain)
• NPU execution precision: INT8 (auto-cast by MWMX toolchain)
• Execution target: NPX6-48K NPU on R-Car X5H

---

Prerequisites

To run inference on Renesas R-Car X5H, you need:

1. Renesas R-Car X5H board with NPX6 NPU
2. Renesas MWMX Runtime
3. Hugging Face CLI to download the model

Download

hf download Renesas/YOLOv11-ONNX --repo-type=model --include "fp32/*"

---

Benchmark Methodology

• HIL runs: Hardware-in-the-loop — measured on physical R-Car X5H silicon via the MWMX runtime (metawaremx_runtime CI pipeline, "APM50" ship-performance target)
• Precision: FP32 ONNX input; INT8 execution (auto-cast by MWMX)
• Slices: only the 1 AI core slice was run for this model; the 12-core slice was skipped in the source export