MMPose RTMPose project (open-mmlab/mmpose)
Source: https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose
Structured fields
{
"archived": false,
"checked_at": "2026-10-17T00:00:00.000Z",
"usefulness": "Real-time multi-person pose framework with body, whole-body (RTMW), face, hand and animal model zoos and speed/accuracy tables; the upstream stack behind DWPose and many pose-control preprocessors.",
"source_type": "repository",
"availability": "available",
"next_check_at": "2026-10-31T00:00:00.000Z",
"known_limitations": [
"Subproject page of a larger repository; archived/maintenance status not checked."
],
"upstream_updated_at": "2025-08-04T07:30:50.000Z"
}Evidence claims
- [upstream_claim] Page describes RTMPose as a high-performance real-time multi-person pose estimation framework built on MMPose; model zoo tables for Body8, WholeBody (RTMPose and RTMW), Animal, Face, Hand. source
- [upstream_claim] Reported figures: RTMPose-m 75.8 COCO AP with 90+ FPS on an Intel i7-11700 CPU and 430+ FPS on a GTX 1660 Ti; RTMPose-s 72.2 AP at 70+ FPS on Snapdragon 865; measured with 5-frame detection interval and no flip test. source
- [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| code | Apache-2.0 | permitted | permitted | permitted | unknown | MMPose license was not visible in the fetched text of this subproject page; check the repository LICENSE. L07 2026-10-17: license_id filled from GitHub API SPDX Apache-2.0 (license file LICENSE). |
| model_weights | unknown | unknown | unknown | unknown | unknown | Checkpoints trained on combined public datasets (Body8 etc.); page does not state checkpoint terms or commercial-use status. |