Closed ttducqt closed 3 years ago
Nice, I didn't know they had released this.
You will have to look at the two tflite files for the front and back model (using Netron, for example) to figure out where the differences are, and then change the PyTorch code.
Will you convert that model soon ? I can't wait it !!! >.<
I have no plans to do this any time soon. I'm happy to take pull requests, though. ;-)
Created the pull request you suggested. It was pretty straightforward thanks to your work (the back model is based on BlazeBlock) and your directions #12
Awesome, I've merged it into the repo.
Hello. Thanks for your work. I see that there is still a blazeface_back model at https://github.com/google/mediapipe/blob/master/mediapipe/models/face_detection_back.tflite, how should i implement ?