Scaled-YOLOv4 (ONNX) – Renesas X5H

Introduction

This repository hosts Scaled-YOLOv4 targeting the Renesas R-Car X5H platform for object detection inference on the NPX6 NPU.

Model Architecture: Scaled-YOLOv4
Source Model: upstream repo scaledYoloV4 (no HuggingFace mirror of these weights; see model.source in .metadata.yaml)
Task: Object Detection
Dataset: TBD (likely COCO — not confirmed)
Input Resolution: TBD — not available from the source data
Parameters: not published — count them from the ONNX graph (sum(numpy_helper.to_array(t).size for t in model.graph.initializer))

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.

scaledYoloV4_optimized.onnx (FP32)
        │
        └─▶  MWMX Runtime  ──▶  INT8 auto-cast  ──▶  NPX6 NPU

Provided Artifacts

Artifact	Status	Notes
FP32 (ONNX)	✅	`fp32/scaledYoloV4.onnx` — FP32 ONNX export

Performance

Measured on Renesas R-Car X5H via the MWMX runtime (APM80 ship-performance CI pipeline).

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

The 1-AI-core slice failed to compile in the source CI pipeline, so only the 12-core result is available.

Runtime	Precision	Device	Latency (ms)	Type
MWMX Runtime	INT8 (auto)	X5H · 1× NPU · 12 Cores · 850 MHz	13.808	Measured

Reconfirmed: 1-core compile still fails as of the 2026-09-16 benchmark run.

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:

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

Download

hf download Renesas/Scaled-YOLOv4-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, "APM80" ship-performance target)
Precision: FP32 ONNX input; INT8 execution (auto-cast by MWMX)
Slices: only the 12-AI-core result is available (1-core compile failed)

Downloads last month: -; Downloads are not tracked for this model. How to track