Skip to content

Issues: google-ai-edge/mediapipe

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

331 Open 4,756 Closed
331 Open 4,756 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Running on a TV box with poor performance type:others issues not falling in bug, perfromance, support, build and install or feature
#5608 opened Sep 5, 2024 by InitialFStudio
@kuaashish
Whether Mediapipe supports the overall detection of multiple people task:holistic landmarker Issues related to MediaPipe Holistic Landmarker type:feature Enhancement in the New Functionality or Request for a New Solution
#5607 opened Sep 4, 2024 by jhlibra
@kuaashish
Face Landmark Detection on Stiched Image platform:javascript MediaPipe Javascript issues task:face landmarker Issues related to Face Landmarker: Identify facial features for visual effects and avatars. type:support General questions
#5606 opened Sep 4, 2024 by aankur
@kuaashish
Provide bzlmod support platform:c++ Issues specific to C++ framework in mediapipe task::all All tasks of MediaPipe type:feature Enhancement in the New Functionality or Request for a New Solution
#5605 opened Sep 3, 2024 by Algomorph
@kuaashish
3
Desktop examples use the deprecated mediapipe::GlCalculatorHelper::CreateSourceTexture platform:c++ Issues specific to C++ framework in mediapipe type:others issues not falling in bug, perfromance, support, build and install or feature
#5604 opened Sep 3, 2024 by Algomorph
@kuaashish
An error occurred: module 'mediapipe.python._framework_bindings.model_ckpt_util' has no attribute 'GenerateGpuTfLite' platform:python MediaPipe Python issues task:LLM inference Issues related to MediaPipe LLM Inference Gen AI setup type:support General questions
#5603 opened Sep 3, 2024 by akau16
@kuaashish
4
iOS LLM Task SDK is NOT initialized successfully via KMP platform:ios MediaPipe IOS issues task:LLM inference Issues related to MediaPipe LLM Inference Gen AI setup type:support General questions
#5601 opened Sep 2, 2024 by 2BAB
@kuaashish
2
[LLM][falcon_cpu]Failed to run on Android Device (internal:Failed to initialize engine: %s Failed to create engine: INTERNAL:;RET_CHECK failure(mediapipe/tasks/cc/genai/inference/utils/xnn_utils/tflite_weight_accessor.cc:102)tflite_model_ platform:android Issues with Android as Platform task:LLM inference Issues related to MediaPipe LLM Inference Gen AI setup type:support General questions
#5600 opened Sep 2, 2024 by charles-cloud
@kuaashish
2
inconsistent face landmarker detection result legacy:face mesh Issues related to Face Mesh platform:python MediaPipe Python issues stat:awaiting response Waiting for user response type:support General questions
#5599 opened Sep 2, 2024 by gubinfdu
@kuaashish
3
如何将mediapipe手部关键点检测的模型导出为.tflite格式 type:others issues not falling in bug, perfromance, support, build and install or feature
#5598 opened Aug 31, 2024 by Criminal-9527
@kuaashish
1
Use local model file but have an error "Not allowed to load local resource: file:///D:/model/gemma-2b-it-gpu-int4.bin" platform:javascript MediaPipe Javascript issues task:LLM inference Issues related to MediaPipe LLM Inference Gen AI setup type:support General questions
#5597 opened Aug 30, 2024 by akau16
@kuaashish
2
Segmentation fault at TfLiteTensorsToDetectionsCalculator::ProcessCPU legacy:autoflip AutoFlip related issues platform:c++ Issues specific to C++ framework in mediapipe type:support General questions
#5596 opened Aug 29, 2024 by Danil0v3s
@kuaashish
6
Mediapipe Blendshape legacy:face mesh Issues related to Face Mesh os:linux-non-arm Issues on linux distributions which run on x86-64 architecture. DOES NOT include ARM devices. platform:python MediaPipe Python issues type:support General questions
#5595 opened Aug 29, 2024 by sarperkilic
@kuaashish
Support for GEMMA-2-2B-it Model stat:awaiting googler Waiting for Google Engineer's Response task:LLM inference Issues related to MediaPipe LLM Inference Gen AI setup type:feature Enhancement in the New Functionality or Request for a New Solution
#5594 opened Aug 29, 2024 by jfduma
@schmidt-sebastian
2
hand_tracking_gpu build successfully but can't run legacy:hands Hand tracking/gestures/etc os:linux-non-arm Issues on linux distributions which run on x86-64 architecture. DOES NOT include ARM devices. platform:c++ Issues specific to C++ framework in mediapipe type:build/install For Build and Installation issues
#5593 opened Aug 29, 2024 by qinweisen
@kuaashish
1
Use ImageSegmenter instance as reactive leads to exception os:macOS Issues on MacOS platform:javascript MediaPipe Javascript issues task:image segmentation Issues related to image segmentation: Locate objects and create image masks with labels type:bug Bug in the Source Code of MediaPipe Solution
#5592 opened Aug 28, 2024 by amiznikov
@kuaashish
Invalid modifications to min_tracking_combinance and min_detection_combinance os:macOS Issues on MacOS platform:c++ Issues specific to C++ framework in mediapipe task:hand landmarker Issues related to hand landmarker: Identify and track hands and fingers type:support General questions
#5591 opened Aug 28, 2024 by wangweikang3-tal
@kuaashish
1
Gemma 2b converted to tflite seems to produce random results platform:android Issues with Android as Platform task:text classification Issues related to Text Classification: Classify text into relevant tags type:performance Execution Time related type:support General questions
#5590 opened Aug 27, 2024 by AmarOk1412
@kuaashish
2
Android Image Generation Produces Pure Black platform:android Issues with Android as Platform stat:awaiting googler Waiting for Google Engineer's Response task:image generator Issues related to Image generator: lightweight text-to-image generation task type:bug Bug in the Source Code of MediaPipe Solution
#5589 opened Aug 27, 2024 by probable1333
@schmidt-sebastian
1
Inconsistent MediaPipe Tasks Vision version on Maven repository platform:android Issues with Android as Platform task::all All tasks of MediaPipe type:others issues not falling in bug, perfromance, support, build and install or feature
#5588 opened Aug 27, 2024 by ArdeoDeo
@kuaashish
2
Possibility of calculating facial blendshapes from facial landmarks os:linux-non-arm Issues on linux distributions which run on x86-64 architecture. DOES NOT include ARM devices. platform:python MediaPipe Python issues stat:awaiting googler Waiting for Google Engineer's Response task:face landmarker Issues related to Face Landmarker: Identify facial features for visual effects and avatars. type:feature Enhancement in the New Functionality or Request for a New Solution
#5587 opened Aug 26, 2024 by neutronengas
@schmidt-sebastian
1
Draw over mediapipe output using custom shader in Android legacy:object detection Issues related to Object Detection platform:android Issues with Android as Platform type:support General questions
#5585 opened Aug 23, 2024 by pabssen1
@kuaashish
Selective RegionOfInterest isn't available in FaceLandmarker task os:windows MediaPipe issues on Windows platform:javascript MediaPipe Javascript issues task:face landmarker Issues related to Face Landmarker: Identify facial features for visual effects and avatars. type:support General questions
#5584 opened Aug 23, 2024 by RandomUserUsingGitHub
@kuaashish
Error: NOT_FOUND: Input tensor has type float32: it requires specifying NormalizationOptions metadata to preprocess input images.; Initialize was not ok; StartGraph failed platform:python MediaPipe Python issues task:image classification Issues related to Image Classification: Identify content in images and video type:support General questions
#5583 opened Aug 23, 2024 by wanggoldx
@kuaashish
2
How can I run the face landmark model with attention on lips and eyes to provide more accuracy, and additionally output iris landmarks legacy:holistic Issues related to Holistic os:windows MediaPipe issues on Windows platform:c++ Issues specific to C++ framework in mediapipe type:support General questions
#5582 opened Aug 23, 2024 by jhlibra
@kuaashish
1
ProTip! Mix and match filters to narrow down what you’re looking for.