mediapipe icon indicating copy to clipboard operation
mediapipe copied to clipboard

Cross-platform, customizable ML solutions for live and streaming media.

Results 687 mediapipe issues
Sort by recently updated
recently updated
newest added

I'm reviewing Mediapipe as a potential solution for non-Android embedded GPU inference (using an Adreno GPU) and wanted to ask some basic questions: * Is the implementation for GPU inference...

type:support
gpu
stat:awaiting response
task:LLM inference

### Have I written custom code (as opposed to using a stock example script provided in MediaPipe) Yes ### OS Platform and Distribution Android OS 9 ### MediaPipe Tasks SDK...

type:support
platform:android
stat:awaiting response
platform:javascript
task:face detection

### OS Platform and Distribution Linux Ubuntu 22.04 ### Compiler version _No response_ ### Programming Language and version Kotlin JVM target 1.8 ### Installed using virtualenv? pip? Conda?(if python) _No...

type:build/install
platform:android
stat:awaiting response
os:linux-non-arm
task:LLM inference

### Have I written custom code (as opposed to using a stock example script provided in MediaPipe) None ### OS Platform and Distribution mac os ### Mobile device if the...

stat:awaiting response
platform:python
platform:c++
type:bug
os:macOS
task:LLM inference

### Have I written custom code (as opposed to using a stock example script provided in MediaPipe) None ### OS Platform and Distribution ubuntu 20.04 ### MediaPipe Tasks SDK version...

type:support
stat:awaiting response
legacy:face mesh
platform:python
stale
os:linux-non-arm

### Description of issue (what needs changing) code example is misleading with 2 poses in webcam ### Clear description the demo sets numPoses=2, but for webcam you clear the canvas...

type:support
stat:awaiting response
platform:javascript
task:pose landmarker

Version 0.10.12 is available on npm https://www.npmjs.com/package/@mediapipe/tasks-vision but pypi is still at 0.10.11 https://pypi.org/project/mediapipe/

type:support
task::all
stat:awaiting response
platform:python

I've been trying to use Mediapipe detection model with Tkinter but the result is a very laggy video. Here is the code I'm using: import cv2 from custom_funcs import mediapipe_detection...

type:support
stat:awaiting response
platform:python
legacy:holistic
stale

### Have I written custom code (as opposed to using a stock example script provided in MediaPipe) None ### OS Platform and Distribution linux ### MediaPipe Tasks SDK version 0.10.11...

type:support
platform:python
task:gesture recognition
os:linux-non-arm

### OS Platform and Distribution M1 MacBook Air, macOS Monterey ### Compiler version Apple clang version 13.1.6 (clang-1316.0.21.2.3) ### Programming Language and version C++ ### Installed using virtualenv? pip? Conda?(if...

type:build/install
stat:awaiting response
legacy:face mesh
platform:c++
stale
os:macOS