PlantNet-300K-ResNet18-OpenVINO

PlantNet-300K-ResNet18 for Intel NPUs, GPUs and CPUs: plantnet from litert-community/PlantNet-300K-ResNet18-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 1.10 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
`plantnet.onnx`	46,968,479	`53bbc7d65df5ce97eeffd7b49443fcd1a9849ce66c3c2171387a07dd42a2917e`
`openvino/plantnet.xml`	199,720	`5327c5c328382024c7e90cd9159a1add1f1418619a20c75ac7d12d40df58e03d`
`openvino/plantnet.bin`	46,905,196	`cd52235f1309df1a1babf8ff5bd7e7b33d2c5e456a6207ab0e59482ef6d970af`
`npu/plantnet.blob`	23,937,153	`ccfef9f016f18cd49c7de17037a3a9384798e19dbcfe94400bc510aacc3983e9`

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`)	1.10	0.02	PASS (cos ≥ 0.9999)
Intel AI Boost NPU	ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1	`.onnx`, compiled when the session loads	1.35	0.68	PASS (cos ≥ 0.9999)
Intel Graphics (iGPU)	ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1	`.onnx`	1.14	0.37	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)	1.35	1.12	PASS (cos ≥ 0.9999)
RTX 5080 Laptop (95 W limit)	ONNX Runtime 1.31.1, CUDA EP	`.onnx`	1.56	1.13	PASS (cos ≥ 0.9999)
Core Ultra 9 386H CPU	ONNX Runtime 1.31.1, CPU EP	`.onnx`	3.93	0.11	reference
Snapdragon X2 Elite NPU	Qualcomm AI Hub, precompiled QNN ONNX	`.onnx` compiled by AI Hub	0.48	0.36	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	0.48	0.85	not compared (AI Hub profile job, 2026-10-30)
Galaxy S26 NPU	Qualcomm AI Hub, precompiled QNN ONNX	`.onnx` compiled by AI Hub	0.53	0.15	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/PlantNet-300K-ResNet18-OpenVINO --local-dir PlantNet-300K-ResNet18-OpenVINO
cd PlantNet-300K-ResNet18-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/plantnet.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/plantnet.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("plantnet.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])