Stack Overflow
Stack Overflow

Questions tagged [mediapipe]

When you are facing any implementation issue for mediapipe in your android, iOS or desktop application, When you want any clarification on concept , methods on mediapipe etc ask question with this tag.

MediaPipe is a framework for building multimodal (eg. video, audio, any time series data), cross platform (i.e Android, iOS, web, edge devices) applied ML pipelines. With MediaPipe, a perception pipeline can be built as a graph of modular components, including, for instance, inference models (e.g., TensorFlow, TFLite) and media processing functions.

585 questions
5
votes
0 answers

Is there a sample project that illustrates using MediaPipe AAR on an ArFragment (sceneform)?

the idea is to track the users' face and augment it with 3d models. MediaPipe would run on the camera feed from arFragment to provide the info necessary to place a 3d model in the arFragment. Is there a sample project that combines MediaPipe and…
Someone Somewhere
  • 23,475
  • 11
  • 118
  • 166
5
votes
6 answers

Cannot install "mediapipe" library

I am trying pip3 install mediapipe but I am getting an error: ERROR: Could not find a version that satisfies the requirement mediapipe ERROR: No matching distribution found for mediapipe My Python version is 3.7.9 and pip version is 20.3.1.
Max
  • 91
  • 1
  • 2
  • 9
5
votes
1 answer

what does it mean to use DEFINE_string

DEFINE_string( calculator_graph_config_file, "", "Name of file containing text format CalculatorGraphConfig proto."); This is part of a code offered by Google's mediapipe for image recognition can someone tell me what this (DEFINE_string)…
Aniket Vishwakarma
  • 89
  • 1
  • 7
4
votes
1 answer

how to fix "from mediapipe.python._framework_bindings import resource_util ImportError: DLL load failed: The specified module could not be found."

When I try to import the mediapipe module which I successfully installed using "pip install mediapipe" I'm getting this error: Traceback (most recent call last): File "", line 1, in File…
I-ter
  • 41
  • 3
4
votes
0 answers

Bazel build `ios_framework` export headers from dependencies

I'm trying to build a ios_framework. It use OpencvFramework. But I don't know how to export headers from Opencv to reuse it My BUILD file load("@build_bazel_rules_apple//apple:ios.bzl", "ios_framework") ios_framework( name = "IrisTracker", …
Robert
  • 45
  • 3
4
votes
3 answers

How to convert Mediapipe Face Mesh to Blendshape weight

I would like to apply facial motions which are predicted by Mediapipe Face Mesh into 3D models using blendshape. Target 3D models have blendshapes like ARFaceAnchor.BlendShapeLocation of iOS. I should convert Face landmark to blendshape weight. To…
49hack
  • 41
  • 1
  • 2
4
votes
2 answers

Issues compiling mediapipe with pyinstaller on macos

I have issues compiling a project with mediapipe via pyinstaller on macos so far I tried: pyinstaller --windowed --noconsole pose_edge.py pyinstaller --onefile --windowed --noconsole pose_edge.py pyinstaller --noconsole pose_edge.py The .app…
Felox
  • 503
  • 3
  • 10
  • 23
4
votes
1 answer

How to run mediapipe facemesh on a ES6 node.js environment alike react

I am trying to run this HTML example https://codepen.io/mediapipe/details/KKgVaPJ from https://google.github.io/mediapipe/solutions/face_mesh#javascript-solution-api in a create react application. I have already done: npm install of all the…
Lorenzo SU
  • 45
  • 2
  • 5
4
votes
1 answer

create a rectangle around all the points returned from mediapipe hand landmark detection just like cv2.boundingrect does

I am using following code to detect hand landmarks using mediapipe import cv2 import mediapipe as mp mphands = mp.solutions.hands hands = mphands.Hands() mp_drawing = mp.solutions.drawing_utils cap = cv2.VideoCapture(0) while True: _, frame =…
Parv Jain
  • 85
  • 2
  • 6
4
votes
0 answers

How to use non camera YUV stream as input to google mediapipe execution pipline graph?

I am working on Mediapipe real time Hand tracking application in for android. Provided demo is using Camera input from SurfaceTexture's ExternalOES I want to use network stream which is coming from webrtc. Network stream is in YUV_I420 format so I…
Afsar edrisy
  • 1,985
  • 12
  • 28
3
votes
0 answers

Is it possible to improve the texturing of mediapipe 3D face mesh?

I'm working on an AR makeup application, using google's mediapipe technology, with attention mesh. For most things it works really well. However, I'm finding that the texture coordinates are really cramped together around the lips and teeth. This…
Dennis L
  • 1,713
  • 14
  • 21
3
votes
1 answer

How to remove face mesh from holistic mediapipe to get better performance

I'm working on holistic mediapipe model (javascript API), it utilizes the pose, face and hand landmark models in MediaPipe Pose, MediaPipe Face Mesh and MediaPipe Hands respectively to generate a total of 543 landmarks (33 pose landmarks, 468 face…
Ayoub Benayache
  • 1,046
  • 12
  • 28
3
votes
0 answers

A/libc: Fatal signal 11 (SIGSEGV), code 1 (SEGV_MAPERR), fault addr 0x0 in tid 26201 (mediapipe_gl_ru), pid 26095 (apps.faceeffect)

This is the two related method: absl::Status Open(CalculatorContext* cc) override { ... return gpu_helper_.RunInGlContext([&]() -> absl::Status { const auto& options =…
di wing
  • 91
  • 5
3
votes
1 answer

How can i add image by mediapipe.js or tensorflow.js?

how can i add image by mediapipe.js or tensorflow.js like previous photo Or how can I add a picture to the body or the human face For example, I want to add glasses and accessories, change clothes, etc.
Abdullah Shokr
  • 39
  • 5
3
votes
0 answers

Mediapipe Face Mesh landmarks visibility and presence attribute values are always 0

I'm working with mediapipe face mesh landmarks model. What I want is to find the 468 landmarks for a face and then filter out any faces with occluded landmarks. The model has these attributes defined as landmarks 'visibility' and 'presence'. But…
waleed raza
  • 31
  • 2
1
2
3
…
38 39