| --- |
| license: other |
| library_name: bcdl |
| tags: |
| - rdk-s100 |
| - rdk-s100p |
| - d-robotics |
| - bpu |
| - hbm |
| - image-segmentation |
| - semantic-segmentation |
| --- |
| |
| # PIDNet-S for RDK S100/S100P β real-time semantic segmentation |
|
|
| Compiled BPU models (`.hbm`) for the **D-Robotics RDK S100 / S100P**, ready to |
| load β 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: [PIDNet](https://github.com/XuJiacong/PIDNet)-S, Cityscapes 19 classes |
|
|
| > [!WARNING] |
| > **Non-commercial.** These weights carry a restriction the upstream *code* |
| > licence never mentions β see [Licence](#licence) at the bottom. Redistribution |
| > is permitted; commercial use is not. If you need a commercial build, the |
| > recipe is public and you can retrain or substitute the backbone. |
|
|
| ## Files |
|
|
| | file | what it is | |
| |---|---| |
| | `pidnet_s_nashm_1024x2048_nv12_v3.hbm` | 2048x1024 NV12, 19 classes β 18.0 MB | |
|
|
| ## Measured on an S100P |
|
|
| | stage | latency | throughput | |
| |---|---|---| |
| | segmentation | 4.48 ms | 223 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** β 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("pidnet_s_nashm_1024x2048_nv12_v3.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 β see the |
| [Python API](https://github.com/ruisv/bcdl/blob/main/docs/API.md) |
| ([δΈζ](https://github.com/ruisv/bcdl/blob/main/docs/API.zh.md)). |
|
|
| ## What to know before deploying |
|
|
| **11x faster than the DeepLabV3+ build it replaces** (4.48 ms against 49.6 ms) at |
| half the model size, for a 0.9859 output cosine and 94.6% pixel agreement. |
|
|
| The output is at 1/8 resolution β `[1, 19, 128, 256]` β and the label map is |
| upsampled by the caller. Argmax costs 0.18 ms here, so folding it into the graph |
| would buy nothing. |
|
|
| **The `_v3` suffix is load-bearing.** Earlier builds were calibrated on data that |
| had not been pre-normalised. When `cal_data_type` is float32 the compiler's |
| `norm_type` does **not** apply to the calibration data, so the input thresholds |
| come out wrong β and the model still compiles without a warning and segments to |
| noise. If you rebuild this, check the input threshold in `quant_info.json`. |
|
|
| **Non-commercial.** See the licence note above. |
|
|
| ## Licence |
|
|
| MIT on the code, but the weights are trained on **Cityscapes**, whose terms permit distributing a trained model and bar commercial use of it in the same breath. |
|
|
| **BCDL itself is Apache-2.0 and is unrelated to these terms** β it is a |
| general-purpose runtime that loads any `.hbm`. The licence above constrains |
| *these weights and this compiled artefact*. |
|
|
| The conversion recipe β ONNX export, calibration, `hb_compile` config and the |
| acceptance numbers β 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. |
|
|
