mediapipe
mediapipe copied to clipboard
googlesamples
Implement holistic landmarker example
Description
This pull request adds a new holistic landmarker API
Checklist
- [x] My code follows the code style of the project.
- [x] I have updated the documentation (if applicable).
Type of Change
Please check the relevant option below:
- [x] New feature (non-breaking change which adds functionality)
Screenshots
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).
View this failed invocation of the CLA check for more information.
For the most up to date status, view the checks section at the bottom of the pull request.
![google-cla[bot] avatar](https://avatars.githubusercontent.com/in/42202?v=4 "Published by a pub.dev verified publisher"){kind=small}
UI comment: the peek window height should be adjusted. We don't need to show the inference time below the expanding arrow until the developer has expanded the bottom sheet.
UI: If the blendshapes option is off, let's hide the blendshapes '--' empty adapter
Edit: just saw the email about the segmentation crash, so sending it to eng to verify.
Does this API support more than 1 person at a time? If so, we should give the dev an option to view 1-3 different poses.
@schmidt-sebastian I am seeing a lot of "Replacing 305 out of 305 node(s) with delegate (unknown) node, yielding 1 partitions for the whole graph." in our logs, though numbers vary. Is this expected? I also noticed pose detection completely fails if a face isn't detected (even when I lower the face detection threshold to 0)
Does this API support more than 1 person at a time? If so, we should give the dev an option to view 1-3 different poses.
@PaulTR I'm afraid not, our detecting API only return one person at a time.