Upload MoViNet-A0-Stream-OpenVINO: ONNX, OpenVINO IR, Intel NPU blob, card and manifest
450fb52 verified | license: apache-2.0 | |
| base_model: litert-community/MoViNet-A0-Stream-LiteRT | |
| base_model_relation: quantized | |
| library_name: openvino | |
| pipeline_tag: video-classification | |
| tags: | |
| - openvino | |
| - onnx | |
| - intel-npu | |
| # MoViNet-A0-Stream-OpenVINO | |
| MoViNet-A0-Stream for Intel NPUs, GPUs and CPUs: movinet_a0_stream from [litert-community/MoViNet-A0-Stream-LiteRT](https://huggingface.co/litert-community/MoViNet-A0-Stream-LiteRT/tree/a21743c58801227b8265f47b136cb096fe22989d) 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 3.23 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 | | |
| |---|---|---| | |
| | `movinet_a0_stream.onnx` | 15,243,826 | `65afaf7f1f9f1ea3f200162e9b3c6b907ae27bfb246d3b6f789469ea98346928` | | |
| | `openvino/movinet_a0_stream.xml` | 1,105,346 | `1c70aeb6f915b25b0ece110faea4684170ca1954b3d027ba908e946975e8eda7` | | |
| | `openvino/movinet_a0_stream.bin` | 14,974,864 | `c2ab939b05f93788adf5ff7e3591e5ae06aafaaa30534a01e1730cefcd418f78` | | |
| | `npu/movinet_a0_stream.blob` | 12,055,168 | `fea7dd41cbaf7788dff8cc8017933377257f982aa6b163d8c5257318694c11ae` | | |
| 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`) | 3.23 | 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 | 2.32 | 1.81 | PASS (cos ≥ 0.9999) | | |
| | Intel Graphics (iGPU) | ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1 | `.onnx` | 10.21 | 2.45 | FAIL: output_0_output: cos 0.1238 < 0.99; output_0_output: argmax agreement 0/1; output_24_output: cos 0.1543 < 0.99; output_25_output: cos 0.3649 < 0.99; output_26_output: cos 0.5257 < 0.99; output_27_output: cos -0.3138 < 0.99 | | |
| | RTX 5080 Laptop (95 W limit) | ONNX Runtime 1.31.1, CUDA EP | fp16 copy of the `.onnx` (not in this repo) | 6.97 | 1.19 | PASS (cos ≥ 0.9999) | | |
| | RTX 5080 Laptop (95 W limit) | ONNX Runtime 1.31.1, CUDA EP | `.onnx` | 6.33 | 1.16 | PASS (cos ≥ 0.9999) | | |
| | Core Ultra 9 386H CPU | ONNX Runtime 1.31.1, CPU EP | `.onnx` | 3.49 | 0.11 | reference | | |
| | Snapdragon X2 Elite NPU | Qualcomm AI Hub, precompiled QNN ONNX | `.onnx` compiled by AI Hub | 1.29 | 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 | 1.14 | 2.04 | not compared (AI Hub profile job, 2026-10-30) | | |
| | Galaxy S26 NPU | Qualcomm AI Hub, precompiled QNN ONNX | `.onnx` compiled by AI Hub | 1.11 | 0.16 | 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/MoViNet-A0-Stream-OpenVINO --local-dir MoViNet-A0-Stream-OpenVINO | |
| cd MoViNet-A0-Stream-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/movinet_a0_stream.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/movinet_a0_stream.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("movinet_a0_stream.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/MoViNet-A0-Stream-LiteRT](https://huggingface.co/litert-community/MoViNet-A0-Stream-LiteRT). | |