license: apache-2.0
base_model: litert-community/DIS-ISNet-LiteRT
base_model_relation: quantized
library_name: openvino
pipeline_tag: image-segmentation
tags:
- openvino
- onnx
- intel-npu
DIS-ISNet-OpenVINO
DIS-ISNet for Intel NPUs, GPUs and CPUs: dis from litert-community/DIS-ISNet-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 41.77 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 |
|---|---|---|
dis.onnx |
176,368,980 | 4101d87d06f48169718b0a6dbe844b0c861b69289493f9ed6fe9e5ec08dda95e |
openvino/dis.xml |
1,138,382 | 91ab641e25eeab1d359379038a8a5d4428a99e3ac7aa4ade28c72dd600b367da |
openvino/dis.bin |
176,019,080 | df408e5ef680a4a0e393ab11a2263de656610f075bf1dc5483f440bfb5d38e30 |
npu/dis.blob |
110,022,785 | b521145f276f138242427719ef127b443ac3689858a5ef34f18c12bbd8e246d8 |
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), 2026-11-07. 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) |
41.77 | 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 |
40.92 | 60.40 | PASS (cos ≥ 0.9999) |
| Intel Graphics (iGPU) | ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1 | .onnx |
30.17 | 2.94 | 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) |
20.54 | 1.13 | PASS (cos ≥ 0.9999) |
| RTX 5080 Laptop (95 W limit) | ONNX Runtime 1.31.1, CUDA EP | .onnx |
32.05 | 1.14 | PASS (cos ≥ 0.9999) |
| Core Ultra 9 386H CPU | ONNX Runtime 1.31.1, CPU EP | .onnx |
1040.20 | 0.30 | reference |
| Snapdragon X2 Elite NPU | Qualcomm AI Hub, precompiled QNN ONNX | .onnx compiled by AI Hub |
21.53 | 0.37 | 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 |
21.52 | 9.28 | not compared (AI Hub profile job, 2026-10-30) |
| Galaxy S26 NPU | Qualcomm AI Hub, precompiled QNN ONNX | .onnx compiled by AI Hub |
19.17 | 0.26 | 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/DIS-ISNet-OpenVINO --local-dir DIS-ISNet-OpenVINO
cd DIS-ISNet-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/dis.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/dis.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("dis.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/DIS-ISNet-LiteRT.