MediaPipe Pose Landmarker (full, float16, v1), mirrored for Rostrum
Google's MediaPipe Pose Landmarker (full model, float16, version 1): a person detector plus BlazePose GHUM 3D landmark model in one .task bundle, finding 33 body points per frame.
This repository is a pinned, public copy of the exact files the Rostrum apps download. Rostrum fetches each file at a fixed commit of this repository and checks its SHA-256 before use.
What Rostrum uses it for
3D's mocap from video: it finds a person's body points in each frame, and the points become a clip on a rig. It only reads pictures, it never makes them.
Rostrum uses it for analysis only, never generation: it reads what is in a recording or a picture and makes no new sound, voice or image.
Files
| File | Bytes | SHA-256 |
|---|---|---|
pose_landmarker_full.task |
9,398,198 | 5134a3aad27a58b93da0088d431f366da362b44e3ccfbe3462b3827a839011b1 |
In Rostrum's models folder they go under pose-landmarker/.
Source
| What | Where | Commit / version |
|---|---|---|
| Exact file (unchanged copy) | https://storage.googleapis.com/mediapipe-models/pose_landmarker/pose_landmarker_full/float16/1/pose_landmarker_full.task | version 1 (the pinned address) |
| Original project, Google | https://github.com/google-ai-edge/mediapipe | 1a35fe914f9cd3ddea9aa7c014a08ec3dd2a8399 (master when mirrored) |
| Documentation | https://ai.google.dev/edge/mediapipe/solutions/vision/pose_landmarker |
Authors
Google (MediaPipe; BlazePose GHUM 3D).
Licence
Apache-2.0 (LICENSE, from the MediaPipe repository). File redistributed unchanged.