YOLOv5mu

aries-rb/ holds the MXQ reproduced from the published arxiv folder (https://github.com/mobilint/mblt-model-arxiv/tree/main/models/object_detection/YOLOv5mu). 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 single, so it supports the core mode(s) single only.

It was evaluated with qbruntime 1.5.0 in async inference mode on coco (5000 samples): map50_95 0.48226, map50 0.6501. Only the evaluated core mode was measured.

SHA-256: fd028751f414546c1a39419fdf3948a3ff287249df8caa71fb265a3ddfed575d (26301384 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": "YOLOv5mu",
  "variant": "c0923-base",
  "qbcompiler": "1.3.0",
  "qbruntime": "1.5.0",
  "compile": {
    "image_tag": "1.3-cuda12.8.1-ubuntu22.04",
    "image_digest": "sha256:6ad69aaa9581487ac6a1864b88d4c2179c7a4a486a3ab1ac376dbdfe763415e7",
    "inference_scheme": "single",
    "device": "gpu"
  },
  "evaluation": {
    "dataset": "coco",
    "sample_count": 5000,
    "primary": {
      "map50_95": 0.48226
    },
    "secondary": {
      "map50": 0.6501
    },
    "protocol": null,
    "eval_data_identity": null,
    "identity_audit": "absent",
    "inference_mode": "async",
    "image_tag": "1.3-cpu-ubuntu22.04",
    "image_digest": "sha256:7c25b894fc0807acdf27f15c61b910b96dc66d3f5d97e04b595b2d7a8008e77c"
  },
  "retention_percent": {
    "map50_95": 98.56926787393208
  },
  "content_sha256": "7be828d14c57b978b1dcb73c3125f0f72534e6dc217511edc7e0b111f7737dc7",
  "attempt_id": "srcmodes19-yolov5mu-20261012t131946",
  "superseded_attempt_ids": [],
  "sha256": "fd028751f414546c1a39419fdf3948a3ff287249df8caa71fb265a3ddfed575d",
  "format": "MXQv7",
  "supported_modes": [
    "single"
  ],
  "size": 26301384,
  "ops_commits": {
    "selection": "2505304b714b87f620665f0d55ac9ce99d6c57e6"
  },
  "arxiv_folder": "https://github.com/mobilint/mblt-model-arxiv/tree/main/models/object_detection/YOLOv5mu",
  "publication": {
    "status": "public",
    "reason": "approved"
  }
}
Downloads last month
73
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mobilint/YOLOv5mu

Quantized
(35)
this model

Collection including mobilint/YOLOv5mu