mediapipe
mediapipe copied to clipboard
Cross-platform, customizable ML solutions for live and streaming media.
### Have I written custom code (as opposed to using a stock example script provided in MediaPipe) None ### OS Platform and Distribution Ubuntu 22.04 ### Mobile device if the...
### Description of issue (what needs changing) Multiple Person Pose Detection isn't written from Mediapipe ### Clear description Pose Detection Model is made by single person detection model, but I...
### Have I written custom code (as opposed to using a stock example script provided in MediaPipe) None ### OS Platform and Distribution MacOS ### Mobile device if the issue...
### Have I written custom code (as opposed to using a stock example script provided in MediaPipe) None ### OS Platform and Distribution Linux Ubuntu 20 ### MediaPipe Tasks SDK...
- The links that are supposed to redirect to the corresponding solution-api page are being redirected to the 'Not Found' page. - Links to the broken link page: https://github.com/google/mediapipe/blob/master/docs/getting_started/javascript.md#Ready-to-use-JavaScript-Solutions https://github.com/google/mediapipe/blob/master/docs/getting_started/python.md#Ready-to-use-Python-Solutions
### MediaPipe Solution (you are using) Mediapipe Tasks ### Programming language Kotlin ### Are you willing to contribute it No ### Describe the feature and the current behaviour/state Would be...
I am trying to understand the [canonical face model](https://github.com/google/mediapipe/blob/a908d668c730da128dfa8d9f6bd25d519d006692/mediapipe/modules/face_geometry/data/canonical_face_model.obj). I tried to project the vt coordinates but I am not getting the right landmark indices. Please see the following code...
libdc1394-22 has been removed, and is superseded by libdc1394. Ref. https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=963924 This fixes the inability to run the script on newer systems, as `libdc1394-22` no longer exists.
### Solution Holistic ### Describe the actual behavior When using the `holistic` solution, the calculator first estimates the body pose and three points for each hand (`wrist`, `index mcp` and...
Otherwise, the visualizer fails https://viz.mediapipe.dev/