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

Let's say I'm building a web application which uses a bundler like [Vite](https://vite.dev) and depends on @mediapipe/tasks-vision for image segmentation. The recommended way of constructing a WASM fileset is to...

type:feature
platform:javascript

### MediaPipe Solution (you are using) [email protected] ### Programming language TypeScript ### Are you willing to contribute it None ### Describe the feature and the current behavior/state I want to...

type:feature
platform:javascript
stat:awaiting googler
task:pose landmarker

### OS Platform and Distribution Linux ARM64 ### Compiler version _No response_ ### Programming Language and version Python ### Installed using virtualenv? pip? Conda?(if python) _No response_ ### MediaPipe version...

type:build/install
platform:python
stat:awaiting googler
os:linux-non-arm

I have experimented with pip installation of MediaPipe to Windows 11. 1. factory reset the laptop and boot Pure Windows 11 2. install Python 3.12.8 from the Python official website...

os:windows
platform:python
type:bug
stat:awaiting googler

This pull request enabled multi-class NMS for object detectors in vision package, for all APIs including iOS, Java, Python and web. Also included in this pull request: - Fixed Dockerfile.manylinux_2_28_x86_64...

### Description of issue (what needs changing) _No response_ ### Clear description I'm running the Hand Landmark Detection sample code but got this issue. ### Correct links https://github.com/google-ai-edge/mediapipe-samples/blob/main/examples/hand_landmarker/python/hand_landmarker.ipynb ### Parameters...

platform:python
type:bug
stat:awaiting googler
task:hand landmarker

Is there way for media pipe detect eye landmarks when given video of close up of an eye? It seems that it always needs the whole face.

type:support
task:face landmarker

### Have I written custom code (as opposed to using a stock example script provided in MediaPipe) None ### OS Platform and Distribution Linux ### MediaPipe version _No response_ ###...

type:support
platform:python
stat:awaiting googler
task:pose landmarker

I noticed the palm landmark connections in the documentation did not correlate with the Python implementation. It's implemented as (1,5) in python but the docs show it should be (0,5)....

### Have I written custom code (as opposed to using a stock example script provided in MediaPipe) None ### OS Platform and Distribution MacOS 15 (ARM) ### Python Version 3.12...

platform:python
type:modelmaker
task:gesture recognition
os:macOS