mediapipe
mediapipe copied to clipboard
googlesamples
Testing device: > Pixel 4 Testing model: > gemma-2b-it-gpu-int4.bin and other gpu models Log: > Load model error: internal: Failed to initialize engine: %sUNKNOWN: Failed to build program executable -...
We have identified a memory leak in the segmentAsync method of the ImageSegmentService class. The issue occurs during the invocation of the segmentAsync(image:timestampInMilliseconds:) method provided by the library. This leak...
Hi, I’m working on a Raspberry Pi 5 with the Hailo-8L accelerator (13 TOPS) and I need to convert a MediaPipe model from .task to .hef, specifically: pose_landmarker_lite.task → pose_landmarker_lite.hef...
based on the https://github.com/google-ai-edge/mediapipe-samples/tree/main/examples/pose_landmarker/android, can mediapipe detecting multi person pose?
I followed the [tutorial](https://ai.google.dev/edge/mediapipe/solutions/customization/gesture_recognizer) to customize the gesture recognition to include open, close, none. when I actually tested it it came up with category=' '.  
## difficulty i was researching how to [cache a model on the web](https://developers.googleblog.com/en/7-dos-and-donts-of-using-ml-on-the-web-with-mediapipe/#:~:text=or%20IndexedDB%20to-,cache%20the%20model,-and%20binary%20so) and followed a link in the blog post to see how a [touchless ATM sample app on...
The Model of input size is 256 x 256 x 3 (shown in spec), but BitmapImageBuilder can can accept a bitmap of any size. How dose it work ? (Change...
I found a picture from the following blog about the virtual try-on of cosmetic contact lenses implemented by mediapipe, but I did not find the relevant specific code implementation. How...
### Discussed in https://github.com/google-ai-edge/mediapipe-samples/discussions/494 Originally posted by **walterf25** January 24, 2025 I 'am able to build and run the PoseLandmarker example in xcode, but I am trying to create a...
I called it this way and got an error. How should I solve it modelPath = [[NSBundle mainBundle] pathForResource:@"pose_landmarker_full"ofType:@"task"inDirectory:@"Data/Raw/DLModels"];MPPPoseLandmarkerOptions *poseLandmarkerOptions = [[MPPPoseLandmarkerOptions alloc] init];poseLandmarkerOptions.baseOptions.modelAssetPath = modelPath;poseLandmarkerOptions.numPoses = 1;poseLandmarkerOptions.minPoseDetectionConfidence = 0.5;poseLandmarkerOptions.minPosePresenceConfidence...
