Amit Moryossef

Hi, When storing a dataset in a disk-mapped fashion with TFDS, we store poses as three objects: - fps: float - data: tensor of floats - confidence: tensor of floats...

Hi! I could write a utility for that. First, however, I would like to know why you want to use JSON files? They are larger, require more disk I/O operations,...

If you would like to save your pose as a file, you can do: ```python with open("example.pose", "wb") as f: pose.write(f) ``` And then in Blender, with python, you can...

For the language pair `de-ch`, it generates Mediapipe poses. These can be used for the 3D avatar.

This project can be used to replace the machine learning model: https://rdtr01.xl.digital/

Thanks @AymaneZizi , I didn't try any of those. I think the goal would be to control this 3D avatar using poses as input

To continue, see: https://github.com/mozilla/firefox-translations-training/issues/586

https://github.com/AmitMY/pose-docker/tree/master/Google You don't have to use docker, the code to run once you have this repository installed is: https://github.com/AmitMY/pose-docker/blob/master/Google/api/pose_video.py And there is a utility file for joint positions: https://github.com/AmitMY/pose-docker/blob/master/Google/api/pose_util.py

It only adds the `ios-src` when you open the site from iOS (emulator or real device), because of the way my caching system works for offline usage. In order to...

While I understand your solution - I think that addressing it explicitly will cause problems for other users (as in, it will be fixed for me, but others might encounter...