YOLOv6-S (ONNX) – Renesas X5H

Introduction

This repository hosts YOLOv6-S, targeting the Renesas R-Car X5H platform for object detection inference on the NPX6 NPU.

Note: The other YOLOv6 sizes (YOLOv6-M-ONNX, YOLOv6-L-ONNX) each have their own sibling repo.

Model Architecture: YOLOv6, SyncBN, "fast" training recipe
Source Model: OpenMMLab config yolov6_s_syncbn_fast_8xb32_300e_coco (no HuggingFace mirror of these weights; see model.source in .metadata.yaml)
Task: Object Detection
Dataset: COCO (inferred from checkpoint name)
Input Resolution: TBD
Parameters: 18.5M

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.

yolov6s_..._optimized.onnx (FP32)
        │
        └─▶  MWMX Runtime  ──▶  INT8 auto-cast  ──▶  NPX6 NPU

Provided Artifacts

Artifact	Status	Notes
FP32 (ONNX)	✅	`fp32/yolov6s.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	12.077511	Measured
MWMX Runtime	INT8 (auto)	X5H · 1× NPU · 12 Cores · 850 MHz	9.560201	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. YOLOv6 produces multi-scale detection tensors that require decoding and Non-Maximum Suppression (NMS) postprocessing.

Postprocessing

Anchor-free box decoding at each output scale
Confidence threshold filtering
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:

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

Download

hf download Renesas/YOLOv6-S-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: both 1-core and 12-core results reported

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