---
license: apache-2.0
tags:
- object-detection
- onnx
- rk3588
- rknn
---

# 🚀 RKNN Object Detection Models

ONNX + RKNN models for object detection, optimized for Rockchip RK3588 NPU deployment via [rknn_model_zoo](https://github.com/airockchip/rknn_model_zoo).

## 📦 Models

### ONNX (Universal Format)

| Model | File | Architecture | Size | Source |
|:------|:-----|:-------------|-----:|:-------|
| YOLOX-S | `yolox/yolox_s.onnx` | CNN | ~24 MB | [examples/yolox](https://github.com/airockchip/rknn_model_zoo/tree/main/examples/yolox) |
| YOLOX-M | `yolox/yolox_m.onnx` | CNN | ~68 MB | [examples/yolox](https://github.com/airockchip/rknn_model_zoo/tree/main/examples/yolox) |
| PP-YOLOE-S | `ppyoloe/ppyoloe_s.onnx` | CNN | ~24 MB | [examples/ppyoloe](https://github.com/airockchip/rknn_model_zoo/tree/main/examples/ppyoloe) |
| PP-YOLOE-M | `ppyoloe/ppyoloe_m.onnx` | CNN | ~68 MB | [examples/ppyoloe](https://github.com/airockchip/rknn_model_zoo/tree/main/examples/ppyoloe) |

### RKNN (RK3588 NPU Format, INT8 Quantized)

| Model | File | Quantization | Size | Tool |
|:------|:-----|:-------------|-----:|:-----|
| YOLOX-S | `yolox/yolox_s.rknn` | INT8 | ~11 MB | rknn-toolkit2 2.3.2 |
| YOLOX-M | `yolox/yolox_m.rknn` | INT8 | ~27 MB | rknn-toolkit2 2.3.2 |
| PP-YOLOE-S | `ppyoloe/ppyoloe_s.rknn` | INT8 | ~9.3 MB | rknn-toolkit2 2.3.2 |
| PP-YOLOE-M | `ppyoloe/ppyoloe_m.rknn` | INT8 | ~25 MB | rknn-toolkit2 2.3.2 |

> RKNN files are converted from ONNX with INT8 quantization. Input/output dtype changed from float32 to int8 for NPU performance.

### Original Download URLs

| Model | ONNX | 
|:------|:-----|
| YOLOX-S | [yolox_s.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolox/yolox_s.onnx) |
| YOLOX-M | [yolox_m.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/yolox/yolox_m.onnx) |
| PP-YOLOE-S | [ppyoloe_s.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/ppyoloe/ppyoloe_s.onnx) |
| PP-YOLOE-M | [ppyoloe_m.onnx](https://ftrg.zbox.filez.com/v2/delivery/data/95f00b0fc900458ba134f8b180b3f7a1/examples/ppyoloe/ppyoloe_m.onnx) |

## 📥 Download

```python
from huggingface_hub import hf_hub_download

# Download ONNX (universal)
hf_hub_download(repo_id="eebyp/RKNN", filename="yolox/yolox_s.onnx", local_dir="./model")

# Download RKNN (RK3588 NPU, INT8)
hf_hub_download(repo_id="eebyp/RKNN", filename="yolox/yolox_s.rknn", local_dir="./model")
```

## 🔗 Source

- **Repository**: [airockchip/rknn_model_zoo](https://github.com/airockchip/rknn_model_zoo)
- **Platform**: RK3562 / RK3566 / RK3568 / RK3576 / RK3588
- **Conversion**: rknn-toolkit2 2.3.2, target_platform=rk3588, INT8 quantization

## 📄 License

Apache 2.0

---

> **Note:** This repository is hosted for **personal research purposes only**. For production use, please refer to the official repository above.