Renesas/YOLOv8-X-ONNX

YOLOv8-X (ONNX) – Renesas X5H

Introduction

This repository hosts YOLOv8-X, targeting the Renesas R-Car X5H platform for object detection inference on the NPX6 NPU.

• Model Architecture: YOLOv8-X — anchor-free, decoupled-head YOLO variant
• Source Model: Ultralytics/YOLOv8 — upstream repo yolov8x (COCO)
• Task: Object Detection
• Dataset: COCO (inferred from checkpoint name)
• Input Resolution: TBD
• Parameters: 68.2M (published Ultralytics YOLOv8-X figure)

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.

yolov8x_..._optimized.onnx (FP32)
        │
        └─▶  MWMX Runtime  ──▶  INT8 auto-cast  ──▶  NPX6 NPU

Provided Artifacts

Artifact	Status	Notes
FP32 (ONNX)	✅	fp32/yolov8x.onnx — FP32 ONNX export

Performance

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

Benchmark configuration: Single NPU · Batch size: 1 · Input resolution: TBD

Runtime	Precision	Device	Latency (ms)	Type
MWMX Runtime	INT8 (auto)	X5H · 1× NPU · 1 Core · 850 MHz	74.328378	Measured
MWMX Runtime	INT8 (auto)	X5H · 1× NPU · 12 Cores · 850 MHz	44.857536	Measured

---

Model Input

Input Tensor

• Shape: TBD — not available from source data (expected (N, 3, H, W), RGB)
• Format: TBD
• Data Type: TBD
• Pixel Range: TBD

Preprocessing

TBD — not available from source data.

Model Outputs

TBD — not available from source data. YOLOv8 produces multi-scale decoupled detection head outputs (classification and box regression via distribution focal loss) that require decoding and Non-Maximum Suppression (NMS) postprocessing.

Postprocessing

1. Decode predictions per detection head (DFL box decoding)
2. Confidence threshold filtering
3. Non-Maximum Suppression (NMS)

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/YOLOv8-X-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: results reported for both 1 AI core and 12 AI cores per NPU instance