README.md

---
license: apache-2.0
library_name: bcdl
tags:
- rdk-s100
- rdk-s100p
- d-robotics
- bpu
- hbm
- ocr
- text-recognition
---

# PP-OCRv5 for RDK S100/S100P — detection + recognition + angle

Compiled BPU models (`.hbm`) for the **D-Robotics RDK S100 / S100P**, ready to
load — no ONNX export, no calibration, no `hb_compile`. Built and measured with
[**BCDL**](https://github.com/ruisv/bcdl), a C++17 inference and media library
for the RDK S-series with Python bindings.

Upstream: [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR) PP-OCRv5 server

> [!TIP]
> **Redistributable, including commercially.** The licence chain was checked on
> the code, the pretrained weights it started from, and the data it was trained
> on — all three, because a permissive repository badge does not by itself say
> anything about the weights. See [Licence](#licence).

## Files

| file | what it is |
|---|---|
| `ppocrv5_server_det_960x960.hbm` | text detection, 960x960 — 33.7 MB |
| `ppocrv5_server_rec_48x320.hbm` | recognition, 48x320 — 24.8 MB |
| `ppocrv5_lcnet_cls_80x160.hbm` | textline angle 0/180 — 2.3 MB |
| `ppocr_keys_v5_18385.txt` | dictionary — required by the recogniser |

## Measured on an S100P

| stage | latency | throughput |
|---|---|---|
| detection | 19.86 ms | 50 FPS |
| recognition | 4.83 ms | 207 FPS |
| angle classifier | 0.37 ms | 2710 FPS |

`hrt_model_exec perf`, one thread, minimum of three runs, on a board first gated
against its own previously recorded numbers. **BPU time only** — CPU
pre/post-processing is on top and is listed per task in BCDL's
[benchmark results](https://github.com/ruisv/bcdl/blob/main/benchmarks/RESULTS.md).

## Use it

```bash
conda install -c https://mirrors.ruis.ai/conda -c conda-forge bcdl
```

```python
import bcdl
engine = bcdl.Engine("ppocrv5_server_det_960x960.hbm")
print(engine.input_shape(0), engine.output_shape(0))
```

Each task has a decoder in BCDL that turns those raw outputs into boxes,
keypoints, masks, disparity or text — see the
[Python API](https://github.com/ruisv/bcdl/blob/main/docs/API.md)
([中文](https://github.com/ruisv/bcdl/blob/main/docs/API.zh.md)).

## What to know before deploying

**Prefer v6 unless you need something here.** The v6 package is faster and more
accurate for detection and recognition. This one is kept for two reasons: it is
a fallback, and its **angle classifier is the one v6 does not ship** — the same
file appears in the v6 package for that reason.

The dictionary is version-specific: v5 recognises 18385 classes. The matching
key file ships here.

## Licence

Apache-2.0, on the code and on every model card.

**BCDL itself is Apache-2.0 and is unrelated to these terms** — it is a
general-purpose runtime that loads any `.hbm`. The licence above constrains
*these weights and this compiled artefact*.

The conversion recipe — ONNX export, calibration, `hb_compile` config and the
acceptance numbers — is public in
[**bcdl-model-zoo**](https://github.com/ruisv/bcdl-model-zoo), so this build can
be reproduced or retargeted rather than taken on trust.