google-ai-edge/mediapipe
Cross-platform, customizable ML solutions for live and streaming media.
C++Apache-2.0
Issues
- 2
- 6
Support for macOS Swift?
#5644 opened by yiyinglai - 0
Create custom task mediapipe
#5648 opened by RansomBroker - 0
The MediaPipe Tasks Vision 0.10.16 package doesn´t have the wasm folder in the jsDelivr CDN
#5647 opened by olalinv - 0
can i build custom task, on mediapipe ?
#5646 opened by RansomBroker - 7
Lack of documentation for compiling MediaPipe as a TensorFlow.js WASM package
#5613 opened by ginesmartinezros - 1
Iris detection demo does not work out-of-the-box
#5645 opened by TakhirMamirov - 5
Language Dedtection documents link is broken
#5632 opened by sajjadrahman56 - 3
- 2
- 2
TypeError: Super constructor null of nJ is not a constructor (for ImageSegmenter initialization)
#5638 opened by vastava - 6
- 9
how to build com.google.mediapipe:tasks-genai for android..need steps please
#5633 opened by BalajiPolisetty2207 - 1
New warning NORM_RECT without IMAGE_DIMENSIONS for face/pose landmarks with 0.10.15
#5639 opened by eyaler - 1
Detect "looking back" using mediapipe Python API
#5641 opened by monajalal - 2
Use local model file but have an error "Not allowed to load local resource: file:///D:/model/gemma-2b-it-gpu-int4.bin"
#5597 opened by akau16 - 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_
#5600 opened by charles-cloud - 2
iOS LLM Task SDK is NOT initialized successfully via KMP
#5601 opened by 2BAB - 1
Can't find hand_landmark.tflite
#5615 opened by Criminal-9527 - 7
Running tasks-vision on Mac Chrome Web Worker crashes
#5631 opened by joacopaz - 1
- 6
Support for GEMMA-2-2B-it Model
#5594 opened by jfduma - 1
face_mesh dll error
#5642 opened by xcjcb001 - 3
如何将mediapipe手部关键点检测的模型导出为.tflite格式
#5598 opened by Criminal-9527 - 10
Support Gemma2-2b model for inference in Android
#5610 opened by FranzKafkaYu - 4
- 3
- 4
Running on a TV box with poor performance
#5608 opened by InitialFStudio - 2
Android/Java PoseLandmarker unnecessary []byte garbage
#5624 opened by calbot - 6
inconsistent face landmarker detection result
#5599 opened by gubinfdu - 3
- 2
extensive memory usage while running mediapipe hand landmarker and custom object detection
#5626 opened by AlundorZhu - 9
Update the docs to show how to build tasks_vision Android
#5628 opened by calbot - 3
Docker mediapipe image build fails
#5627 opened by calbot - 0
Explanation of output shape [1, 117] (World landmarks for pose) or [1, 195] (Pose landmarks) of pose_landmarks_detector.tflite in Mediapipe
#5622 opened by mbkamran - 5
An error occurred: module 'mediapipe.python._framework_bindings.model_ckpt_util' has no attribute 'GenerateGpuTfLite'
#5603 opened by akau16 - 1
Face Landmark Detection on Stiched Image
#5606 opened by aankur - 3
- 4
Model Maker Supportting for Image Segmentation
#5617 opened by consistent1997 - 2
Mediapipe don't work with 'VIDEO' mode on Android WebView while 'IMAGE' mode work very well.
#5618 opened by ffpwserver - 0
What is the output of the `hand_detector.tflite` file using the hand landmark detection model `hand_landmark.task` locally?
#5616 opened by Criminal-9527 - 5
Provide bzlmod support
#5605 opened by Algomorph - 2
Desktop examples use the deprecated mediapipe::GlCalculatorHelper::CreateSourceTexture
#5604 opened by Algomorph - 4
hand_tracking_gpu build successfully but can't run
#5593 opened by qinweisen - 0
I can modify the recognized categories by modifying the calculator(TfLiteTensorsToDetectionsCalculator)
#5611 opened by tisaud - 1
INTERNAL: Service "kGpuService", required by node mediapipe_tasks_vision_pose_landmarker_poselandmarkergraph__mediapipe_tasks_vision_pose_detector_posedetectorgraph...
#5609 opened by V-m1r - 6
- 0
Mediapipe Blendshape
#5595 opened by sarperkilic - 0
- 0
Invalid modifications to min_tracking_combinance and min_detection_combinance
#5591 opened by wangweikang3-tal