mobilint/YOLOv8m-face

YOLOv8m_face

aries-rb/ holds the MXQ reproduced from the published arxiv folder (https://github.com/mobilint/mblt-model-arxiv/tree/main/models/face_detection/YOLOv8m_face). It was compiled by qbcompiler 1.3.0 in the image mobilint/qbcompiler:1.3-cuda12.8.1-ubuntu22.04 (sha256:6ad69aaa9581487ac6a1864b88d4c2179c7a4a486a3ab1ac376dbdfe763415e7) with --inference-scheme all, so it supports the core mode(s) single, multi, global4, global8 only.

It was evaluated with qbruntime 1.5.0 in async inference mode on widerface (3226 samples): hard_ap 0.87199, easy_ap 0.95745, medium_ap 0.94767. Only the evaluated core mode was measured.

SHA-256: 59e9396e3aa029267711944fb80a12269beed4b4873f04808946854fe645d21a (34668445 bytes). Verify a download with sha256sum <file>.mxq and compare the digest with this value and with aries-rb/metadata.json.

aries-rb/best_result.json contains legacy build values and is retained for mblt-vision-python compile defaults. The legacy aries/ directory was removed; mblt-model-zoo <= 2.12 must pin an older revision.

{
  "schema_version": 2,
  "model": "YOLOv8m_face",
  "variant": "gptq",
  "qbcompiler": "1.3.0",
  "qbruntime": "1.5.0",
  "compile": {
    "image_tag": "1.3-cuda12.8.1-ubuntu22.04",
    "image_digest": "sha256:6ad69aaa9581487ac6a1864b88d4c2179c7a4a486a3ab1ac376dbdfe763415e7",
    "inference_scheme": "all",
    "device": "gpu"
  },
  "evaluation": {
    "dataset": "widerface",
    "sample_count": 3226,
    "primary": {
      "hard_ap": 0.87199
    },
    "secondary": {
      "easy_ap": 0.95745,
      "medium_ap": 0.94767
    },
    "protocol": null,
    "eval_data_identity": {
      "annotation_sha256": "4dedbd4eb5d00dafe5fdae9040014dc5ed04eeb493ed7661d6804bc87d9089d0",
      "sample_list_sha256": "2e8cd912637ea1af513fd8203d0f195eb500593fb4eb4918e116da0562266519"
    },
    "identity_audit": "verified",
    "inference_mode": "async",
    "image_tag": "1.3-cpu-ubuntu22.04",
    "image_digest": "sha256:7c25b894fc0807acdf27f15c61b910b96dc66d3f5d97e04b595b2d7a8008e77c"
  },
  "retention_percent": {
    "hard_ap": 98.45318339373821
  },
  "content_sha256": "eaef496f5de6a8fbd98740fca9e0a26c8363fd99f9fb026c25eb440f03f1e043",
  "attempt_id": "YOLOv8m_face-jinman-coreall-d04038015c1d",
  "superseded_attempt_ids": [],
  "sha256": "59e9396e3aa029267711944fb80a12269beed4b4873f04808946854fe645d21a",
  "format": "MXQv7",
  "supported_modes": [
    "single",
    "multi",
    "global4",
    "global8"
  ],
  "size": 34668445,
  "ops_commits": {
    "selection": "d642f96eda9bcd0a04ac02d8b73b28aecfc0311f"
  },
  "arxiv_folder": "https://github.com/mobilint/mblt-model-arxiv/tree/main/models/face_detection/YOLOv8m_face",
  "publication": {
    "status": "public",
    "reason": "approved"
  }
}