| --- |
| license: apache-2.0 |
| base_model: litert-community/ormbg-LiteRT |
| base_model_relation: quantized |
| library_name: openvino |
| pipeline_tag: image-segmentation |
| tags: |
| - openvino |
| - onnx |
| - intel-npu |
| --- |
| |
| # ormbg-OpenVINO |
|
|
| ormbg for Intel NPUs, GPUs and CPUs: ormbg from [litert-community/ormbg-LiteRT](https://huggingface.co/litert-community/ormbg-LiteRT/tree/8dfdacc4ebceafd4d55195fdbd3baf8470610518) as ONNX (tf2onnx 1.17.0, opset 17), OpenVINO IR with fp32 weights, and a precompiled Intel NPU blob. On the NPU of a Core Ultra 9 386H the blob runs in 41.37 ms per run, numpy input to numpy output. |
|
|
| Scripts, raw records, and the same table for all 52 graphs of LiteRT-Models: https://github.com/john-rocky/windows-zoo |
|
|
| ## Files |
|
|
| | file | bytes | sha256 | |
| |---|---|---| |
| | `ormbg.onnx` | 176,402,496 | `2690a9ba100433374b8787c7c4d3946ca5b9494bb5b993b6c5a27f12599ce1d9` | |
| | `openvino/ormbg.xml` | 1,170,698 | `7a3eedc9150171e62cc899ee1c19762d5929b2443953bc2f90bb5031ee6911b4` | |
| | `openvino/ormbg.bin` | 176,019,080 | `a9c42ae5c189911601f2c88885178d172f012aa5366652f9e29a8cc3c8c1212a` | |
| | `npu/ormbg.blob` | 110,010,497 | `80cec8c06002add0d1d3493f4f8ad79943d4e74388b9d82d21033947c0c3950d` | |
|
|
| The NPU blob was compiled with OpenVINO 2026.4.1, Intel NPU driver 32.0.100.4841 (OpenVINO reports NPU_DRIVER_VERSION 1004841, NPU_COMPILER_VERSION 524292). If `import_model` refuses a blob on another driver or OpenVINO version, compile the IR instead (the commented line in the snippet). |
|
|
| ## How it was measured |
|
|
| MSI Stealth 16 AI+ (Core Ultra 9 386H, RTX 5080 Laptop GPU at a 95 W power limit, Windows 11 build 26200.9711, on AC power), 2026-11-06 to 2026-11-07. On the laptop, each row is one process: load, one run, 5 warmup runs, then the median of 30 timed runs (2 warmup + 10 timed runs when the first run takes more than 3 s), numpy input to numpy output, every runtime at its default settings, one process at a time, each started after the CPU, the RTX and the Intel GPU had gone idle (the thresholds are in METHOD.md of the GitHub repo). Output check: each output against the CPU output in fp32 on the same input (ONNX Runtime's CPU EP); PASS = cosine ≥ 0.99, no NaN or Inf, and top-1 agreement ≥ 0.99 for class scores. The Snapdragon rows are Qualcomm AI Hub profile jobs of the same ONNX files (their own timer). |
|
|
| ## Speed and output check |
|
|
| | processor | runtime | file | ms | load s | output check | |
| |---|---|---|---|---|---| |
| | Intel AI Boost NPU | OpenVINO 2026.4.1 | `npu/` blob (`import_model`) | 41.37 | 0.06 | PASS (cos ≥ 0.9999) | |
| | Intel AI Boost NPU | ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1 | `.onnx`, compiled when the session loads | 41.21 | 63.98 | PASS (cos ≥ 0.9999) | |
| | Intel Graphics (iGPU) | ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1 | `.onnx` | 29.45 | 2.84 | PASS (cos ≥ 0.9999) | |
| | RTX 5080 Laptop (95 W limit) | ONNX Runtime 1.31.1, CUDA EP | fp16 copy of the `.onnx` (not in this repo) | 19.76 | 1.12 | PASS (cos ≥ 0.9999) | |
| | RTX 5080 Laptop (95 W limit) | ONNX Runtime 1.31.1, CUDA EP | `.onnx` | 32.22 | 1.13 | PASS (cos ≥ 0.9999) | |
| | Core Ultra 9 386H CPU | ONNX Runtime 1.31.1, CPU EP | `.onnx` | 1022.97 | 0.30 | reference | |
| | Snapdragon X2 Elite NPU | Qualcomm AI Hub, precompiled QNN ONNX | `.onnx` compiled by AI Hub | 21.16 | 0.51 | not compared (AI Hub profile job, 2026-10-30) | |
| | Snapdragon X2 Elite NPU | Qualcomm AI Hub, ONNX Runtime QNN EP | `.onnx`, compiled when it loads | 21.24 | 8.71 | not compared (AI Hub profile job, 2026-10-30) | |
| | Galaxy S26 NPU | Qualcomm AI Hub, precompiled QNN ONNX | `.onnx` compiled by AI Hub | 18.95 | 0.24 | not compared (AI Hub profile job, 2026-10-30) | |
|
|
| The ONNX file against the source `.tflite` (LiteRT interpreter on the CPU, the same input): PASS, cosine ≥ 0.9999 for every output. |
|
|
| ## Run it on the Intel NPU |
|
|
| Download this repo, then run the snippets from its folder: |
|
|
| ```sh |
| pip install huggingface_hub |
| hf download mlboydaisuke/ormbg-OpenVINO --local-dir ormbg-OpenVINO |
| cd ormbg-OpenVINO |
| ``` |
|
|
| OpenVINO (`pip install openvino==2026.4.1`): |
|
|
| ```python |
| import numpy as np |
| import openvino as ov |
| |
| core = ov.Core() |
| if "NPU" not in core.available_devices: |
| raise SystemExit(f"no Intel NPU visible to OpenVINO: {core.available_devices}") |
| with open("npu/ormbg.blob", "rb") as f: |
| compiled = core.import_model(f.read(), "NPU") # precompiled: no compile at load |
| # or compile the IR on this machine: compiled = core.compile_model("openvino/ormbg.xml", "NPU") |
| # replace the zeros with your preprocessed input (float32, the shapes printed by compiled.inputs) |
| feeds = {i.get_any_name(): np.zeros(list(i.shape), np.float32) for i in compiled.inputs} |
| outputs = compiled(feeds) |
| print({o.get_any_name(): outputs[o].shape for o in compiled.outputs}) |
| ``` |
|
|
| ONNX Runtime with the OpenVINO EP (`pip install onnxruntime==1.31.1 onnxruntime-ep-openvino==1.8.1`): |
|
|
| ```python |
| import numpy as np |
| import onnxruntime as ort |
| import onnxruntime_ep_openvino as ov_ep |
| |
| ort.register_execution_provider_library(ov_ep.get_ep_name(), ov_ep.get_library_path()) |
| npu = [d for d in ort.get_ep_devices() |
| if d.ep_name == ov_ep.get_ep_name() and d.ep_metadata.get("ov_device") == "NPU"] |
| if not npu: |
| raise SystemExit("no Intel NPU visible to the OpenVINO EP") |
| so = ort.SessionOptions() |
| so.add_provider_for_devices(npu, {}) |
| sess = ort.InferenceSession("ormbg.onnx", sess_options=so) # compiles for the NPU here |
| # replace the zeros with your preprocessed input (float32) |
| feeds = {i.name: np.zeros(i.shape, np.float32) for i in sess.get_inputs()} |
| outputs = sess.run(None, feeds) |
| print([o.shape for o in outputs]) |
| ``` |
|
|
| ## Licence |
|
|
| Apache-2.0, the licence of [litert-community/ormbg-LiteRT](https://huggingface.co/litert-community/ormbg-LiteRT). The upstream model: [schirrmacher/ormbg](https://huggingface.co/schirrmacher/ormbg). |
|
|
