| ---
|
| license: apache-2.0
|
| base_model: []
|
| pipeline_tag: object-detection
|
| tags:
|
| - object-detection
|
| - computer-vision
|
| - renesas
|
| - x5h
|
| - onnx
|
| - centernet
|
| - resnet18
|
| - detection
|
| ---
|
|
|
| # CenterNet-R18 (ONNX) – Renesas X5H
|
|
|
| ## Introduction
|
|
|
| This repository hosts **CenterNet** with a **ResNet18** backbone, targeting the **Renesas
|
| R-Car X5H** platform for object detection inference on the NPX6 NPU.
|
|
|
| - **Model Architecture:** CenterNet — keypoint-based, anchor-free object detector, ResNet18 backbone
|
| - **Source Model:** OpenMMLab config [`centernet_resnet18_140e_coco`](https://github.com/open-mmlab/mmdetection/blob/main/configs/centernet/metafile.yml)
|
| *(no HuggingFace mirror of these weights; see `model.source` in `.metadata.yaml`)*
|
| - **Task:** Object Detection
|
| - **Dataset:** COCO (inferred from checkpoint name)
|
| - **Input Resolution:** 512 × 512 (inferred from `crop512` in the checkpoint name)
|
| - **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.
|
|
|
| ```
|
| centernet_r18_..._optimized.onnx (FP32)
|
| │
|
| └─▶ MWMX Runtime ──▶ INT8 auto-cast ──▶ NPX6 NPU
|
| ```
|
|
|
| ## Provided Artifacts
|
|
|
| | Artifact | Status | Notes |
|
| |----------|--------|-------|
|
| | **FP32 (ONNX)** | ✅ Published | `fp32/centernet_r18_8xb16_crop512_140e_coco.onnx` — auto-cast to INT8 by the MWMX toolchain at compile time (see Deployment Flow above); no separate INT8 file is shipped |
|
|
|
| ## 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 × 512 × 512 (inferred)
|
|
|
| | Runtime | Precision | Device | Latency (ms) | Type |
|
| |---------|-----------|--------|---------------|------|
|
| | MWMX Runtime | INT8 (auto) | X5H · 1× NPU · 1 Core · 850 MHz | 11.978 | Measured |
|
| | MWMX Runtime | INT8 (auto) | X5H · 1× NPU · 1 Core · 850 MHz | 11.989 | Measured (2026-09-16) |
|
| | MWMX Runtime | INT8 (auto) | X5H · 1× NPU · 12 Cores · 850 MHz | 3.467 | Measured |
|
|
|
| ### 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
|
|
|
| ```bash
|
| hf download Renesas/CenterNet-R18-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:** results reported for both 1 AI core and 12 AI cores per NPU instance
|
|
|
