Repository Issue Activity (beta)

#6065 Export wasm files from exports field in @mediapipe/tasks-vision

#4423 bject_detector.Dataset.from_pascal_voc_folder ignores negative/background images

#6270 `RuntimeError: memory access out of bounds` loading gemma-4-E2B-it-web.task on Chrome 146 / macOS / Apple M4

#5622 Explanation of output shape [1, 117] (World landmarks for pose) or [1, 195] (Pose landmarks) of pose_landmarks_detector.tflite in Mediapipe

#5751 What do the circle points on the overlayview mean

#5616 What is the output of the `hand_detector.tflite` file using the hand landmark detection model `hand_landmark.task` locally?

#5880 models/hand_landmarker.task doesn't exist

#5763 Processing Images Using pose_world_landmarks in MediaPipe to Extract 3D Coordinates and Map Them to Unity

#6209 `is_multilabel` is not a valid parameter

#5996 Improving MediaPipe Lite Pose Detection in Fog and Low Light

#5786 classifications are not working properly in Audio stream

#5789 Reducing Latency for Hand-Tracking Solution in Python

#6138 R8 Proguard issue

#6306 Clarify Web Tasks Vision telemetry and Pose Landmarker model redistribution terms

#5908 MediaPipe Face Mesh Not Working on Galaxy S25 Ultra

#6252 [iOS] Add cancel/stop generation API for LlmInference

#6276 SIGSEGV in AndroidPacketCreator.nativeCreateRgbaImage called from ModelResourcesCacheService.nativeInstallServiceObject

#5774 CalculatorGraph::Run() faild on my Android Chrome browser

#5709 Unable to replicate medipipe inference

#6305 hand landmark_full.tflite raw output of screen landmarks is in **pixel space [0, 224]**, not normalized [0, 1] ?

#5584 Selective RegionOfInterest isn't available in FaceLandmarker task

#6304 What's the difference between MediaPipe Pose Estimation and MLKit Pose Estimation?

#5787 Issue with Protobuf and OpenCV 4 Compatibility on macOS

#5917 @mediapipe/tasks-text: highest version is old

#5943 Build Failure on macOS 15.2 due to incompatible zlib version