Downloads · 30 days
0
ruisv/bcdl-las2-stereo
bcdl-las2-stereo is a depth estimation model from ruisv. Use it for the depth estimation task on the model card, and read the license before you ship it in a product. It is set up for bcdl. The card lists the license as mit.
Compiled BPU models (.hbm) for the D-Robotics RDK S100 / S100P, ready to load — no ONNX export, no calibration, no hbcompile. Built and measured with BCDL, a C++17 inference and media library for the RDK S-series with…
Downloads · 30 days
0
Access
Public
Updated Aug 13, 2026
Repo size
81.9 MB
Likes
0
Public
Click a slice to open those files.
.hbm81.9 MB · 100%
From the Hugging Face model README
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, a C++17 inference and media library
for the RDK S-series with Python bindings.
Upstream: Lite Any Stereo V2 (M)
[!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.
| file | what it is |
|---|---|
las2_m_crop_nashm.hbm | centre-crop-fit calibration, 640x480 — 38.8 MB |
las2_m_int16_nashm.hbm | resize-fit calibration, 640x480 — 39.3 MB |
| stage | latency | throughput |
|---|---|---|
| either build | 13.70 ms | 73 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.
conda install -c https://mirrors.ruis.ai/conda -c conda-forge bcdl
import bcdl
engine = bcdl.Engine("las2_m_crop_nashm.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 (中文).
Two calibration modes, and you must match the one you letterbox with. _crop
was calibrated on centre-cropped pairs and _int16 on resize-fitted ones; feed a
build the geometry it was not calibrated for and the disparity degrades quietly
rather than failing.
All-2D and feed-forward — no 3-D cost volume — which is exactly why it runs at 73 FPS here. Cost-volume stereo of comparable quality took ~40 s/frame on this part and was abandoned.
MIT on the code and the weights. One thing worth knowing rather than a term passed down: the release was distilled from FoundationStereo, whose NVIDIA licence is research-only. That is upstream's compliance question, but look at it before a commercial build.
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, so this build can
be reproduced or retargeted rather than taken on trust.