| ---
|
| license: apache-2.0
|
| base_model: []
|
| pipeline_tag: object-detection
|
| tags:
|
| - object-detection
|
| - computer-vision
|
| - renesas
|
| - x5h
|
| - onnx
|
| - tao
|
| - resnet34
|
| ---
|
|
|
| # TAO-PeopleNet-R34 (ONNX) – Renesas X5H
|
|
|
| ## Introduction
|
|
|
| This repository hosts **TAO-PeopleNet-R34**, targeting the **Renesas R-Car X5H** platform for
|
| object detection inference on the NPX6 NPU.
|
|
|
| > **Note:** The other TAO networks each have their own sibling repo (`TAO-DashCamNet-R18-ONNX`, `TAO-PeopleNet-R34-ONNX`, `TAO-TrafficCamNet-R18-ONNX`). They are separate products trained on separate data, not precisions of one model.
|
|
|
| - **Model Architecture:** TAO-PeopleNet-R34 — resnet34 backbone
|
| - **Source Model:** NVIDIA NGC [`resnet34_peoplenet`](https://catalog.ngc.nvidia.com/orgs/nvidia/models/peoplenet)
|
| *(no HuggingFace mirror of these weights; see `model.source` in `.metadata.yaml`)*
|
| - **Task:** Object Detection
|
| - **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.
|
|
|
| ```
|
| model.onnx (FP32)
|
| │
|
| └─▶ MWMX Runtime ──▶ INT8 auto-cast ──▶ NPX6 NPU
|
| ```
|
|
|
| ## Provided Artifacts
|
|
|
| | Artifact | Status | Notes |
|
| |----------|--------|-------|
|
| | **FP32 (ONNX)** | ✅ | `fp32/resnet34_peoplenet.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
|
|
|
| | Runtime | Precision | Device | Latency (ms) | Type |
|
| | :----------: | :----------: | :---------------------------------: | :----------: | :------: |
|
| | MWMX Runtime | INT8 (auto) | X5H · 1× NPU · 12 Cores · 850 MHz | 2.781941 | 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/TAO-PeopleNet-R34-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 are reported per NPU core count where both runs compiled
|
|
|
