Upload M-LSD-tiny-OpenVINO: ONNX, OpenVINO IR, Intel NPU blob, card and manifest

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+npu/mlsd_fp16.blob filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,101 @@
+---
+license: apache-2.0
+base_model: litert-community/M-LSD-tiny-LiteRT
+base_model_relation: quantized
+library_name: openvino
+pipeline_tag: image-segmentation
+tags:
+- openvino
+- onnx
+- intel-npu
+---
+
+# M-LSD-tiny-OpenVINO
+
+M-LSD-tiny for Intel NPUs, GPUs and CPUs: mlsd_fp16 from [litert-community/M-LSD-tiny-LiteRT](https://huggingface.co/litert-community/M-LSD-tiny-LiteRT/tree/ae7c5698d5bbef1976aa5a1f7ad7b9b28d324e3c) 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 4.01 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 |
+|---|---|---|
+| `mlsd_fp16.onnx` | 2,637,523 | `73d41b40feb169e88bfa6428c5a4b2c735069d9848538f6d47535483a50c3537` |
+| `openvino/mlsd_fp16.xml` | 491,894 | `62f49c1f55ed324fc54cab087dec7b3e69c4a35a176b14cb532a7f804cf6e0e6` |
+| `openvino/mlsd_fp16.bin` | 2,457,224 | `176fcb1613fe2434e4aab6461eb0b03359cecea60b53970d0110065286eed38e` |
+| `npu/mlsd_fp16.blob` | 2,703,489 | `6c5cbc4581ec2981b608c4d1d65570797cb5d2e5d6a324811d72d333e374cf5c` |
+
+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`) | 4.01 | 0.00 | FAIL: output_0_output: cos -0.2133 < 0.99 |
+| Intel AI Boost NPU | ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1 | `.onnx`, compiled when the session loads | 3.73 | 1.32 | FAIL: output_0_output: cos -0.2133 < 0.99 |
+| Intel Graphics (iGPU) | ONNX Runtime 1.31.1 + OpenVINO EP 1.8.1 | `.onnx` | 2.34 | 0.43 | PASS (cos ≥ 0.9935) |
+| RTX 5080 Laptop (95 W limit) | ONNX Runtime 1.31.1, CUDA EP | fp16 copy of the `.onnx` (not in this repo) | 2.55 | 1.16 | PASS (cos ≥ 0.9995) |
+| RTX 5080 Laptop (95 W limit) | ONNX Runtime 1.31.1, CUDA EP | `.onnx` | 2.87 | 1.14 | PASS (cos ≥ 0.9999) |
+| Core Ultra 9 386H CPU | ONNX Runtime 1.31.1, CPU EP | `.onnx` | 9.50 | 0.02 | reference |
+| Snapdragon X2 Elite NPU | Qualcomm AI Hub, precompiled QNN ONNX | `.onnx` compiled by AI Hub | 1.60 | 0.34 | 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 | 1.59 | 1.51 | not compared (AI Hub profile job, 2026-10-30) |
+| Galaxy S26 NPU | Qualcomm AI Hub, precompiled QNN ONNX | `.onnx` compiled by AI Hub | 1.31 | 0.14 | 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/M-LSD-tiny-OpenVINO --local-dir M-LSD-tiny-OpenVINO
+cd M-LSD-tiny-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/mlsd_fp16.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/mlsd_fp16.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("mlsd_fp16.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/M-LSD-tiny-LiteRT](https://huggingface.co/litert-community/M-LSD-tiny-LiteRT). The source card names the upstream model as `navervision/mlsd` (not a Hugging Face repo).

manifest.json

@@ -0,0 +1,39 @@
+{
+ "source_repo": "litert-community/M-LSD-tiny-LiteRT",
+ "source_revision": "ae7c5698d5bbef1976aa5a1f7ad7b9b28d324e3c",
+ "graphs": {
+  "mlsd_fp16": {
+   "from": "mlsd_fp16",
+   "ir": {
+    "openvino": "2026.4.1-22982-e213a147257-releases/2026/4",
+    "compress_to_fp16": false
+   },
+   "blob_compiled_with": {
+    "openvino": "2026.4.1-22982-e213a147257-releases/2026/4",
+    "FULL_DEVICE_NAME": "Intel(R) AI Boost",
+    "NPU_DRIVER_VERSION": "1004841",
+    "NPU_COMPILER_VERSION": "524292",
+    "NPU_COMPILER_TYPE": "CompilerType.PREFER_PLUGIN",
+    "INFERENCE_PRECISION_HINT": "<Type: 'float16'>"
+   },
+   "files": {
+    "mlsd_fp16.onnx": {
+     "bytes": 2637523,
+     "sha256": "73d41b40feb169e88bfa6428c5a4b2c735069d9848538f6d47535483a50c3537"
+    },
+    "openvino/mlsd_fp16.xml": {
+     "bytes": 491894,
+     "sha256": "62f49c1f55ed324fc54cab087dec7b3e69c4a35a176b14cb532a7f804cf6e0e6"
+    },
+    "openvino/mlsd_fp16.bin": {
+     "bytes": 2457224,
+     "sha256": "176fcb1613fe2434e4aab6461eb0b03359cecea60b53970d0110065286eed38e"
+    },
+    "npu/mlsd_fp16.blob": {
+     "bytes": 2703489,
+     "sha256": "6c5cbc4581ec2981b608c4d1d65570797cb5d2e5d6a324811d72d333e374cf5c"
+    }
+   }
+  }
+ }
+}

mlsd_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73d41b40feb169e88bfa6428c5a4b2c735069d9848538f6d47535483a50c3537
+size 2637523

npu/mlsd_fp16.blob

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c5cbc4581ec2981b608c4d1d65570797cb5d2e5d6a324811d72d333e374cf5c
+size 2703489

openvino/mlsd_fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:176fcb1613fe2434e4aab6461eb0b03359cecea60b53970d0110065286eed38e
+size 2457224