MobileNetV4-Large-r448-ONNX

MobileNetV4-Large-AA (r448) (ONNX) – Renesas X5H

Introduction

This repository hosts MobileNetV4-Large-AA (r448), targeting the Renesas R-Car X5H platform for image-classification inference on the NPX6 NPU.

• Model Architecture: MobileNetV4 (Large, anti-aliased conv variant) — Universal Inverted Bottleneck backbone with blur-pool anti-aliased downsampling, pretrained on ImageNet-12k and fine-tuned on ImageNet-1k at 448x448 input resolution
• Source Model: timm/mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k
• Task: image-classification (dataset: imagenet-1k)

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.

mobilenetv4_conv_aa_large_r448_in12k_ft_in1k.onnx (FP32)
        │
        └─▶  MWMX Runtime  ──▶  INT8 auto-cast  ──▶  NPX6 NPU

Provided Artifacts

Performance

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

Benchmark configuration: Single NPU · Batch size: 1 · Input: 3 × 448 × 448

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/MobileNetV4-Large-r448-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)