Sureshda
Sureshda
Hi @waleedrazakhan92 , As model predicts presence and visibility as x,y values ,to get propobalities you need to apply the sigmoid function on these values so you will get values...
Hi @jimb2834 ,can you share me your code changes to investigate further on this issue.
Hi @Shubhambindal2017 , Present you can figure out mentioned here . you can comment out everything related to face_landmarks from: /graphs/holistic_tracking/holistic_tracking_[X].pbtxt /graphs/holistic_tracking/holistic_tracking_to_render_data.pbtxt /modules/holistic_landmark/holistic_landmark_[X].pbtxt where [X] is cpu or gpu. Probably...
Hi @moorthy-bs , Updating mediapipe to 0.8.0 fixes this bug for all graphs except for iris tracking :) S20 works with hand tracking, face detection and face mesh now with...
Hi @elbakramer , Did you use the Android gradle solution or Android AAR ? We have similar issue which has solution , please refer [this](https://github.com/google/mediapipe/issues/2567) closed issue.
Hi @Omkarrr , Could you please elaborate this issue to investigate more on this.
Hi @ChenLiangChong , Problem will be solved by upgrading gcc compiler. before, my gcc version was 7.* and It works now with gcc 8.* .
Hi @nfadeluca , The error seems to beUnexpected CPU variant for X86 using defaults: x86_64. The AAR you downloaded only supports armeabi and arm64. It doesn't have x86_64 support (mostly...
Hi @nfadeluca , Could you please provide steps to reproduce this issue.
Hi @nfadeluca . Yes, it is to do with android studio and please check this closed issue https://github.com/google/mediapipe/issues/2979.