license: apache-2.0
base_model: litert-community/MODNet-LiteRT
base_model_relation: quantized
library_name: openvino
pipeline_tag: image-segmentation
tags:
- openvino
- onnx
- intel-npu
MODNet-OpenVINO
MODNet for Intel NPUs, GPUs and CPUs: modnet from litert-community/MODNet-LiteRT 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 16.60 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 |
|---|---|---|
modnet.onnx |
26,503,485 | 062f6d9f76a43ec14b67376a2da77d604e9f0968cf835fa190e654875e3fc090 |
openvino/modnet.xml |
1,442,411 | 7488ce4a32b6f4443f33a7e872ee0bdd2de0cb9bbf0f14ceabed05cca47997ab |
openvino/modnet.bin |
25,848,312 | 74ce169252d038dcd11f539a00480ba171c846b63d3114dddf82e3f7b35d6547 |
npu/modnet.blob |
19,796,097 | f3de63c41292d1b2b368035331a220bb9be0f66fc18354b0a0c8584b782c242f |
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) |
16.60 | 0.01 | PASS (cos ≥ 0.9999) |
| Intel AI Boost NPU | ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1 | .onnx, compiled when the session loads |
15.80 | 15.41 | PASS (cos ≥ 0.9999) |
| Intel Graphics (iGPU) | ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1 | .onnx |
32.06 | 2.31 | PASS (cos ≥ 0.9985) |
| RTX 5080 Laptop (95 W limit) | ONNX Runtime 1.31.1, CUDA EP | fp16 copy of the .onnx (not in this repo) |
8.59 | 1.17 | PASS (cos ≥ 0.9997) |
| RTX 5080 Laptop (95 W limit) | ONNX Runtime 1.31.1, CUDA EP | .onnx |
10.79 | 1.20 | PASS (cos ≥ 0.9999) |
| Core Ultra 9 386H CPU | ONNX Runtime 1.31.1, CPU EP | .onnx |
68.72 | 0.15 | reference |
| Snapdragon X2 Elite NPU | Qualcomm AI Hub, precompiled QNN ONNX | .onnx compiled by AI Hub |
8.30 | 0.35 | 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 |
9.76 | 6.63 | not compared (AI Hub profile job, 2026-10-30) |
| Galaxy S26 NPU | Qualcomm AI Hub, precompiled QNN ONNX | .onnx compiled by AI Hub |
8.86 | 0.21 | 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:
pip install huggingface_hub
hf download mlboydaisuke/MODNet-OpenVINO --local-dir MODNet-OpenVINO
cd MODNet-OpenVINO
OpenVINO (pip install openvino==2026.4.1):
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/modnet.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/modnet.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):
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("modnet.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/MODNet-LiteRT.