Build changes

• Updated genai C package visibility

Framework and core calculator improvements

• Prevent UnpackMediaSequenceCalculator from segfaulting on a type of malformed input.
• Updated import statements of llm_inference_engine.h to support C
• Refactor OpenGL 3.1 path out of TensorsToSegmentationCalculator main file.
• Add 'addRawDataSpanToInputSidePacket' and addRawDataSpanToInputStream binding functions.
• Update DotAttention interface to take SelfAttentionWeights
• Remove customized DotAttention
• Update Tensorflow dependency to latest release
• Update InferenceCalculator documentation on DELEGATE side input.

MediaPipe Tasks update

This section should highlight the changes that are done specifically for any platform and don't propagate to other platforms.

Android

• Add LlmInference stats logging
• Changed max_sequence_length naming to max_tokens

iOS

• Added iOS LlmInferenceError, LlmInference, LlmTaskRunner
• Removed init with default params in LlmInferenceOptions
• Updated iOS task runner to delete C LLM Session on deallocation
• Updated variable names in iOS LlmTaskRunner
• Updated access of C LLMSession to fileprivate
• Updated access of some constants in iOS LlmInference
• Removed unwanted iOS BUILD targets
• Added iOS Gen AI build scripts
• Added iOS Gen AI files
• Updated parameter names in LlmSessionConfig create
• Added asynchronous predict and generate function to iOS LLM Task Runner
• Removed decoded response from iOS LlmTaskRunner
• Updated iOS error enum cases
• Updated response generation state logic in iOS LlmInference
• Fixed error handling in iOS LlmInference
• Updated error message in iOS GenAiInferenceError
• Fixed unitialized response array in iOS LlmTaskRunner
• Added podspec templates of the iOS Gen AI framework

Javascript

• Add visibility field in landmark.d.ts
• Update landmark_result.ts with visibility support

Python

• Register model_ckpt_util in Python framework
• Expose HolisticLandmarker module as other modules
• Create empty module if ENABLE_ODML_CONVERTER is not set
• Optimized memory usage for conversion script

Model Maker changes

• Remove jax and torch from model maker requirements.txt
• Use tf model optimization < 0.8.0 due to tf.keras and tf_keras compat issues

MediaPipe Dependencies

• Update WASM files for 0.10.11 release

Build changes

• Fix TensorsToSegmentationCalculator gpu dependencies.
• Open Source build rules for quantization_util
• Added the binary the converter factory to run the model weight conversion.
• Integrates the kMemoryManagerService into ImageToTensorCalculator and InferenceCalculatorDarwinn.
• Updated iOS OpenCV source build to exclude highgui and videoio
• Open source some BUILD rules for Converter package

Framework and core calculator improvements

• Added Face Landmarker C Tasks API and tests
• Added Pose Landmarker C Tasks API
• Use memcpy now for copying data and indicate how the data is stored
• Remove superfluous glFlush().
• Added Face Detector C Tasks API
• Add mediapipe::file::IsDirectory helper
• Deprecate ImageFrame::ByteDepth
• Added files for the Image Segmenter C Tasks API
• Add general support for PathToResourceAsFile to TfLiteModelLoader
• Add CalculatorGraph::SetErrorCallback to receive errors in case of async graph use cases.
• Add JAX as requirements for MediaPipe python package
• Introduces HardwareBufferPool based on the ReusablePool and MultiPool
• Added the base classes for the LLM weight converter.
• Add stdbool import to C API
• Introduces MemoryManagerService with HardwareBufferPool and integrates it into the Tensor class.
• Added the model writer that writes to the weight binary files.
• Fix GlContext (attachments) cleanup in case of a failing GlContext initialization.
• Add option for using variable XNNPACK operators to MediaPipe XNNPACK flags
• Make InferenceCalculatorDarwinn support float and int32 as input data type.
• Adds VectorToTensorCalculator
• Enable HardwareBufferPool only if MEDIAPIPE_TENSOR_USE_AHWB is enabled
• Enables MultiPool and ReusablePool to pass on absl::Status returns originating from object factory methods.
• Adding TENSOR to InferenceCalculatorCpu to remove vector encumbrances
• Update Clang to version 16
• Add ability to preserve output format to GlScalerCalculator
• Add explicit depedency on XNNPACK & cpuinfo
• Update TensorFlow and Android NDK dependency
• Adds MEDIAPIPE_ANDROID_LINK_NATIVE_WINDOW condition to hardware_buffer_android
• Support interpolate flags in image_to_tensor_converter_opencv.
• Add MODEL_VIEW side input to tflite_model_calculator

MediaPipe Tasks update

This section should highlight the changes that are done specifically for any platform and don't propagate to other platforms.

Android

• Added HolisticLandmarker
• Migrate TextGenerator Java API to C Wrapper
• Add LlmTaskRunner to TextGenerator sources
• Don't cache the JNI environment for async calls
• Simplified api interface
• Updates to LLM JNI Layer
• Handle model loading on Android
• Support custom cache dir.
• Pass cacheDir to LLM engine from Java API
• Add "done" field to the Java LLM API
• Removed backend option from JNI layer

iOS

• Updated supported pixel formats in iOS image classifier Documentation
• Removed support for CVPixelBuffer of type 32RGBA
• Added support for creating CVPixelBuffer from C++ Images to iOS MPPImage Utils
• Updated implementation of MPPImage Utils to reduce lines of code
• Added iOS interactive segmenter options, helpers, implmentation and basic tests
• Added iOS Image Embedder API
• Enabled stream mode on iOS pose landmarker
• Fixed issue with iOS Language Detector Prediction Count
• Added iOS language detector to Cocoapods build
• Added cosine similarity method to iOS MPPImagEmbedder
• Updated method signature of MPPImageEmbedderResult initializer
• Added packet validation in MPPImageEmbedderResult+Helpers
• Added tests for creating MPPImage with source type UIImage from C++ Image
• Renamed methods in MPPImageUtilsTests
• Added a new class for iOS Interctive Segmenter Results
• Added iOS interactive segmenter to cocoapods build
• Added method for initializing MPPImages of all source types from MPPImage+TestUtils
• Added support for creating MPImages of sample buffer source type from C++ Images in MPPImage+Utils
• Added provision to initialize MPImages of source type sample buffer to MPImage+TestUtils
• Added tests for initialization of MPImages with source type sample buffer from MPImage+Utils
• Updated documentation of iOS hand landmarker, image embedder, image segmenter, interactive segmenter, object detector
• Added provision to create graph config from task options that use any proto for iOS tasks
• Added new methods to MPPTaskOptionsProtocol.h
• Updated iOS task runner to initialize tasks using MPPTaskInfo
• Updated iOS text task runner to initialize tasks from task Info.
• Updated iOS vision task runner to use new methods from MPPTaskRunner
• Updated MPPTaskOptionsProtocol
• Updated MPPTaskRunner initializer
• Fixed iOS framework conflicts with TensorFlowLiteC and OpenCV CocoaPods
• Fixed issue in installing iOS tasks text and vision libraries in a single project

Javascript

• Extend verifyGraph to be compatible with proto3.
• Add Holistic Landmarker Web API
• Add export declarations to PoseLandmakerResult
• TypeScript: adding VideoFrame typings support to video input
• Guard WaitOnGpu with extra OpenGL checks.
• Explicitly cast at callsite of WebGL context creation to avoid compilation errors with newer Emscripten versions.

Python

• Added Holistic Landmarker Python API
• Support both proto2 and proto3 in task subgraph options configuration, and revised the Holistic Landmarker API's implementation
• Update holistic_landmarker.py
• Documented HolisticLandmarker
• Fixing delegate passing argument in BaseOptions
• Add model_ckpt_util to Python Build script
• Use pybind_library for GenAI Converter build

MediaPipe Dependencies

• Expose MediaPipe's ABSL and Sentencepiece as shared dependencies
• Remove Sentencepiece's LOG function
• Removed unwanted headers from opencv_ios_xcfraemworl_files.bzl
• Update WASM files for 0.10.10 release
• Upgrade TypeScript to 5.3.3

Build changes

• Add libtext and libvision build rules
• Add lib targets for all C vision tasks

Framework and core calculator improvements

• Added files for the Image Embedder C API and tests
• Pass Model Asset Buffer as byte array + length
• Drop default arguments in C API
• Updated the Image Embedder C API and added tests for cosine similarity
• Drop default arguments in Image Embedder C API
• Remove const from input types of C API
• Resolved issues and added a common header to hold all the necessary structures for the vision tasks
• Refactor OpenCV path out of TensorsToSegmentationCalculator main file.
• Add some convenience getters to EglManager.
• Added files for the Object Detector C Tasks API
• Explicitly delete some copy operations to improve compile errors.
• Extract CPU conversion methods into a separate library & add test
• Updated components and their tests in the C Tasks API
• Ensure that releaseGl() is called if prepapreGl throws
• Adding a GpuTestWithParamBase test class to support value parameterized tests
• Added Gesture Recognizer C API and tests
• Holistic Landmarker C++ Graph
• Revised Gesture Recognizer API implementation and associated tests
• Added FreeMemory test for GestureRecognizerResult
• Refactor GestureRecognizerResult conversion for default initialization
• Move LanguageDetectorResult converter to LanguageDetector task
• Add TensorsToSegmentationCalculator test utilities.
• Added Hand Landmarker C Tasks API and tests
• Export java package for hand_roi_refinement_graph_options.
• Fix naming in different files
• Create an explicit GlRuntimeException class

MediaPipe Tasks update

This section should highlight the changes that are done specifically for any platform and don't propagate to other platforms.

Android

• Create shared utilities to construct category lists
• Create shared utilities to construct landmark lists
• Add the result class for the HolisticLandmarker Java API
• HolisticLandmarker Java API
• Add dependency on hand_roi_refinement_graph_options_proto
• Use Java Proto Lite Target for Hand ROI Refinement proto
• Move hand_roi_refinement_graph_options_java_proto_lite to vision lib

iOS

• Added iOS MPPPoseLandmarker.mm
• Added null check for segmentation masks in pose landmarker helper initializer
• Added pose landmarker protobuf utils
• Fixed graph name in iOS language detector
• Added iOS language detector tests
• Added iOS Objective C Pose Landmarker Tests
• Added iOS interactive segmenter options
• Added iOS region of interest
• Added iOS region of interest helpers
• Updated iOS vision/core to add methods for processing region of interest
• Added iOS interactive segmenter header

Javascript

• Creates GpuBuffers around pre-allocated AHardware_Buffer objects.
• Add drawConfidenceMask() to our public API
• Use gl.LINEAR interpolation for confidence masks
• Add missing export declarations to DrawingUtils

Python

• Example updated for mp.Image in documentation
• Added image classifier benchmark
• Updated copyright
• Documented the return value and added percentile to argparser
• Allowed a default value for the model argument
• Added more benchmark scripts for the Tasks Python API
• Code cleanup and revised benchmarking API
• Removed unused param

Model Maker changes

• Add option to omit the checkpoint callback in text classifier.
• Add BinaryAUC metric and Best Checkpoint callback to Text Classifier
• Remove batch dimension from the output of tflite_with_tokenizer in text classifier.

Build changes

• Allow Python to be build on Mac with GPU support

Bazel changes

• Adds an empty skeleton project for iOS docgen.
• Remove pinned versions from deps
• Added files for the Language Detector C API and tests
• Add OnCameraBoundListener and support for landscape orientation to CameraXPreviewHelper
• Removed language_detection_result and moved the necessary containers to language_detector.h
• Detection postprocessing support quantized tensor.
• Adding vector versions of input calls to TS GraphRunner API
• Introduce AlignHandToPoseInWorldCalculator
• Add check to avoid doing illegal memory access from an invalid iterator from std::prev()
• GPU_ORIGIN configurable through base options proto.
• Introduce FixGraphBackEdges utils function.
• Migrate ParseTagAndName to use absl::string_view
• Plumb an optional default Executor and set of input side packets
• Add implementation and tests for Image Classifier C API
• Allow GPU Origin Proto to be build by Maven
• Add a field to GPUBuffer C struct so FFIGen can handle it
• Add scaling support to surface view renderer.
• Remove objc_library from Python build path for Mac GPU build
• Fix internal incensistency in parsing code
• Add CPU tests for TensorsToSegmentationCalculator
• Speed up Python build by only building binary graph
• Don't drop status message in ConvertFromImageFrame
• Use designated initializers for TensorsToSegmentationCalculator tests.
• Adding two new immutable texture GpuBufferFormat types
• TensorsToDetectionsCalculator supports multi clasees for a bbox.
• Move filtering logic of score to ConvertToDetection.
• Add video and live stream processing and tests for Image Classifier C API
• Upgrade to use Gradle 8.4
• Add AT_FIRST_TICK processing to SidePacketToStreamCalculator.

MediaPipe Tasks update

This section should highlight the changes that are done specifically for any platform and don't propagate to other platforms.

Android

• Add GPU Origin proto to Java Tasks Library

iOS

• Added iOS Pose Landmarker result, options and helpers
• Added iOS language detector options, results, and helpers
• Added property to get labels from iOS Image Segmenter
• Added a test for getting labels from iOS image segmenter
• Updated iOS Image Segmenter documentation to use Swift names
• Added pose landmarker result helpers
• Added iOS pose landmarks connections
• Added iOS pose landmarker header
• Updated documentation
• Added language detector result helpers
• Added iOS language detector implementation
• Fixed extra condition check in iOS Image Segmenter Result Helper
• Added iOS Image Segmenter to CocoaPods build
• Fixed deletion of iOS output MPImage buffer in MPImage Utils
• Added GPU support

Javascript

• Add drawCategoryMask() to our public API
• Creates GpuBuffers around pre-allocated AHardware_Buffer objects.
• Allow OffscreenCanvas to be used by DrawingUtils

Python

• Added files for Face Stylizer Unit Tests
• Allow Mac to use GPU Delegate
• Use mp.ImageFormat instead of just ImageFormat
• Support 3-channel RGB images for Mac Python
• Added GPU support on Mac and Linux

Dependency changes

• Update WASM files for 0.10.8 relese

Framework and core calculator improvements

• Fix win32 build break in mediapipe.
• Remove 'awaiting' labels when user issue/PR updated.
• Fix glScalerCalculator not clearing background in FIT mode
• Add cc_binary target for C Libraries
• Only recreate immutable texture when necessary for Android TensorsToSegmentationCalculator.
• Update PackMediaSequenceCalculator to support index feature inputs on the CLIP_MEDIA_ input tag.
• Added concatenate stream, get_vector_item stream, landmarks_to_tensor stream, tensor_to_joints stream utility function.
• Introduce TensorToJointsCalculator and LandmarksTransformationCalculator
• smoothing stream utility function.
• Don't convert nullptr to std::string in C layer
• Fix memory access issue in C layer
• segmentation smoothing stream utility function.
• Populate the classification result output param instead of a copy
• Add tests for C API containers
• Add unit tests for C layer for the input types of Text Classifier
• Add End to End test for Text Classifier C API
• Add error handling to C API
• Added files for the TextEmbedder C API and tests
• See memory of freed result to nullptr
• Smooth pose landmarks
• GlSurfaceViewRenderer: Capture graph output texture
• Prefix status macro implementation with MP_.
• Introduce CombineJointsCalculator and SetJointsVisibilityCalculator
• Add stream API presence utils.
• Fixed some issues with documentation
• Add stream API merge utils.
• Update glog to latest commit

MediaPipe Tasks update

This section should highlight the changes that are done specifically for any platform and don't propagate to other platforms.

Android

• Do not convert milliseconds to microseconds twice
• Fix bug missing SHOW_RESULT in image generator
• Fix depth condition bug when only depth condition is configured.

iOS

• Added iOS face stylizer result, options and header
• Added iOS MPPFileInfo for tests
• Added new initializers for iOS MPPImage in test utils
• Added iOS MPPMask test utils
• Added iOS image segmenter basic Objective C tests
• Updated multiply function in iOS Image Segmenter tests to use C++ vectors
• Fixed premature deallocation of C++ masks in iOS Image Segmenter
• Updated interface of iOS image segmenter
• Added selfie segmentation and running mode tests to image segmenter
• Uncommented live stream test in iOS image segmenter tests
• Updated iOS Face Detector Objective C API names
• Updated iOS Face Landmarker,hand landmarker,Object Detector Objective C API names
• Added iOS Image Segmenter tests for methods with completion handlers
• Added methods to create iOS MPImage with source type UIImage from a C++ image.
• Changed de-allocation method in data provider release callback
• Fixed error messages
• Updated error messages in MPPImage Utils

Javascript

• Add helper to create Connection array
• Add export declaration for FaceDetector
• Add export declaration to FaceDetector.detect()
• Do not use full filename when FileLocator decides which asset to load

Bug fixes

Fixed Pose Landmarker jittering issue

Model Maker changes

Add export_model_with_tokenizer to Text Classifier API.

MediaPipe Dependencies

Update WASM files for 0.10.7 release

Framework and core calculator improvements

• Fix crash in SavePngTestOutput
• Log stack traces for combined CalculatorGraph statuses
• Add a GpuOrigin parameter to TensorConverterCalculator
• Replace some size EXPECTs by ASSERTs
• Add a support for label annotations (image/label/string and image/label/confidence). Also fixed some clang tidy issues.
• Set confidence score of the bounding box label.
• Add setGpuBufferVerticalFlip to GraphRunner TS API
• Remove unsafe cast.
• apply affine transform before drawing, in order to keep constant line width regardless of face cropping.
• Migrate packet messages auto registration to rely on MEDIAPIPE_STATIC_REGISTRATOR_TEMPLATE
• add end loop calculator for image size
• Provide a way to disable static registration using MEDIAPIPE_DISABLE_STATIC_REGISTRATION
• Header for callback_packet_calculator to allow dynamic registration for superusers
• Support more GPU formats in tensor converter calculator.
• Expose stream handlers in headers to allow dynamic registration for superusers
• Expose tool calculators in headers to enable dynamic registration by superusers.
• Dry-Run mode for static registration to make it easier to find all required static registrations
• Fix MediaPipe build in Chromium.
• Swap left and right hand labels.
• Don't access "document" in WebWorker
• Update PackMediaSequenceCalculator to support adding clip/media/id to the MediaSequence.
• update pose rendering
• Update the header information for EnsureMinimumDefaultExecutorStackSize.
• Move stream API loopback to third_party.
• Add pose landmarks constants
• Add an API in model_task_graph to create or use cached model resources.
• Move stream API image_size to third_party.
• Add C++ converters for C Text Classifier API
• Move stream API rect_transformation to third_party.
• Change the image label input from Classification to Detection.
• Update port includes with IWYU to fix clang warnings in code where corresponding ports are used.
• New image test utilities and memory management fixes.
• Add a custom op resolver for fused batch norm.
• Improving throttling logs by providing a node info corresponding to a throttling stream.
• Use ABSL_LOG in MediaPipe.
• Remove reference pointer to prevent using a constant reference in the looped iteration variable
• Remove unnecessary includes in threadpool_std_thread_impl.cc.
• Make cache writes optional in InferenceCalculatorAdvancedGL
• Update PackMediaSequenceCalculator to support setting clip/media/string, clip/media/confidence and clip/label/index.
• Some spelling and grammar fixes in the comments.
• Add notes/warnings for calculators which use dedicated GL contexts.
• Remove video and stream model in face stylizer.
• Move stream API landmarks_projection to third_party.
• Remove video and streaming mode for face stylizer.
• landmarks_to_detection stream utility function.
• Ensure that C header don't import C++ types
• Splitting GraphRunner into public API declared interfaces and private TS impls
• Add option for nearest neighbor interpolation.
• Fixes two issues with file handling on windows:
• Remove uncoditional texture params reset to make float textures handled correctly.
• fixes the non-unicode path of file_helpers on windows
• Modifying tensor_to_vector_float_calculator to take in D_BFLOAT16 values
• Don't define field in ExternalFileHandler that's not used on Windows.
• Clean up TensorConverterCalculator flipping behavior
• Fix win32 build break in mediapipe.

MediaPipe Tasks update

This section should highlight the changes that are done specifically for any platform and don't propagate to other platforms.

Android

• Adds option to use tensor_ahwb in Android vendor processes
• Add output size as parameters in Java ImageSegmenter
• Change SegmentationOptions.builder() to be public
• ImageGenerator Java API
• Provide API/options to show intermediate results and generating progress for Java Image Generator.
• Set enableFlowLimiting to false since only Image model is supported for face stylizer.
• Move loading tasks-vision-jni to individual vision task class

iOS

• Added refactored iOS vision task runner sources
• Removed convenience initializer from refactored MPPVisionTaskRunner
• Updated iOS docs to use swift names in place of objective c names
• Added gesture recognizer and hand landmarker to iOS vision framework
• Fixed directory creation issues in build_ios_framework.sh
• Changed delegate method to optional
• Added iOS image segmenter implementation file
• Updated image segmenter bazel target to add MPPImageSegmenter.mm
• Renamed option in MPPImageSegmenterOptions
• Updated iOS face detector to use refactored vision task runner
• Updated iOS image classifier to use refactored vision task runner
• Changed order of methods in MPPImageSegmenter.mm
• Fixed method call in MPPImageSegmenter.mm
• Updated face landmarker, gesture recognizer,hand landmarker,object detector to use refactored vision task runner
• Replaced the old iOS vision task runner with the refactored task runner
• Updated iOS gesture recognizer documentation to use Swift names
• Updated iOS hand landmarker documentation to use swift names
• Moved iOS MPPHandLandmark enum to MPPHandLandmarker.h
• Fixes iOS hand landmarker connections

Javascript

• vlog default executor and its config usage
• Updates the runners to support wasm-style binary assets files, and allows their URLs to be explicitly specified as part of the WasmFileset.
• Add 'types' to package.json
• Add externs to js_library targets
• Add API exports for MPMask and MPImage
• Add Handedness to JS, C++ and Android API
• Fix missing exports for FilesetResolver and static constants
• Add exports to ImageSegmenterResult and InteractiveSegmenterResult

Python

• Set the default running model to Image for face stylizer.

Bug fixes

• Internal fixes

Model Maker changes

• Add tensorflow-addons to model_maker requirements.txt

• Change to add the w_avg latent code to style encoding before layer swapping. This is a bug in the previous code. Also set training=True for encoder since this affect the encoding performance.

• add metadata writer into face stylizer.

• Refactor text_classifier preprocessor to move away from using classifier_data_lib

• Import image_util for using it in mediapipe face stylizer open sourcing.

• Fix image_util shortcut import line

• Change supported_ops to a Tuple instead of List to match the API definition.

• Add a new from_image API to create face stylizer dataset from a single image. Also deprecate the from_folder API since we only support one-shot use case now.

• Add an API to run inference with face stylizer TF model.

• Check if the image contains valid face that can be aligned for stylization. If not, throw an exception for invalid input image. This is applied to both input stylized face and raw face.

• Add allow_custom_ops to model_util.convert_to_tflite and enable custom ops for face stylizer.

• MediaPipe Dependencies

• Update WASM files for 10.5 release

Build changes

• Fix Halide BUILD rules
• Fix Android build with any Protos

Framework changes

• add symmetric color style option
• InferenceCalculatorAdvancedGL save cache in Open().
• MEDIAPIPE_NODE/SUBGRAPH_IMPLEMENTATION to use common define for registration
• Generalize non-define registration with MEDIAPIPE_STATIC_REGISTRATOR_TEMPLATE
• Discard outdated packets earlier in MuxInputStreamHandler.
• Replace CHECK with RET_CHECK in GetContract() implementation from six calculators.
• Move waitOnCpu and waitOnGpu out of the synchronized block, which can cause deadlock.
• Adding support for 2 things in tensors_to_image_calculator:
• C++ Image segmenter add output size parameters.
• Add C Headers for Text Classifier

MediaPipe Tasks update

This section should highlight the changes that are done specifically for any platform and don't propagate to other platforms.

Android

• Add proto3 Any proto support for Java task api
• Java API add visibility and presence for landmarks.

iOS

• Changed left and right image orientation angles to match iOS UIImageOrientation
• Updated documentation of MPImage
• Added missing headers in ios vision framework build
• Fixed swift name of iOS face landmarker delegate
• Added iOS Image Segmenter Header

Javascript

• Add angle to BoundingBox
• Support WASM asset loading for MediaPipe Task Web
• Update WASM binaries for 0.10.3 release

Model Maker changes

• Model Maker allow core dataset library to handle datasets with unknown sizes.
• No public description
• Add class weights to core hyperparameters and classifier library.
• Move evaluation onto GPU/TPU hardware if available.

MediaPipe Dependencies

• Update glog to 0.6
• Removed internal dependency on OpenCV 3.x, migrating it to OpenCV 4.x

Build changes

• Added gesture_recognizer.task to vision tasks test data

Framework and core calculator improvements

• Log the Bazel build
• Fix tests to work with arch haswell/sandybridge.
• Update base audio/vision tasks api to suuport proto3 graph options.
• Add an option to disable explicit CPU sync for ExternalTextureRenderer
• Add support for int64 constant side package value.
• Deprecate GraphStatus()
• Modify the TensorToImageFrameCalculator to support normalized outputs.
• Add metadata for all PREFIX/image... prefixes.
• Update Tensorflow dependency in MediaPipe
• update face drawing function.
• Speed up TimeSeriesFramerCalculator.
• Add MatrixData as a packet option for ConstantSidePacketCalculatorOptions.
• Fix timestamp computation when copying within first block.
• Fix -Wsign-compare warning in api2/builder.h
• Shows the recently added warning when WaitUntilIdle is called with source nodes only once. Otherwise, it is very spammy as it's shown every frame. Moreover, display the names of the sources, so the warning is more actionable.
• Exposes OpenCV photo lib.
• Add keys for the context that better match the featurelist for text.
• Do not send PreviousLoopback output packets to closed streams
• Add gpu to cpu fallback for tensors_to_detections_calculator.
• Revert Add location info in registry (debug mode only)
• Fix bounds calculation in RefineLandmarksFromHeatMapCalculator
• Add concatenate image vector calculator

MediaPipe Tasks update

This section should highlight the changes that are done specifically for any platform and don't propagate to other platforms.

Android

• Add delegate options to base options for java API and add unit tests for BaseOptions.

iOS

• Added iOS Gesture Recognizer Protobuf utils
• Added iOS Gesture Recognizer ObjC Test for simple recognition
• Added more recognize tests to iOS Gesture Recognizer Objective C tests
• Added convenience method for creating results for tests in MPPGestureRecognizerResult Helpers
• Added MPPHandLandmarkerResult Helpers
• Added MPPConnection
• Added MPPHandLandmarker
• Added MPPHandLandmark
• Renamed iOS gesture recognizer protobuf utils
• Fixed import in iOS gesture recognizer test utils
• Updated MPPHandLandmarker.h to return the hand connections via class mathods
• Add FaceLandmarker iOS API
• Add FaceLandmarker iOS Live Stream API
• Update iOS Gesture Recognizer error assertion
• Updated method names in MPPGestureRecognizer
• Rename MPPFaceLandmarker.m to MPPFaceLandmarker.mm
• Added hand landmarker implementation file and hand landmarker connections
• Updated constant names in MPPHandLandmarkConnections
• Add FaceLandmarker constants for iOS
• Added hand landmarker protobuf utils
• Added iOS Objective C hand landmarker tests
• Added iOS segmentation mask
• Updated documentation of MPPMask
• Added live stream mode tests for iOS Hand Landmarker
• Updated protobuf helper method name in iOS Gesture Recognizer Helpers
• Updated iOS hand landmarker tests
• Updated hand connections in iOS hand landmarker to class properties.
• Updated signature of initializer in MPPMask
• Fixed float calculations in MPPMask
• Removed generic methods for alloc and memcpy from MPPMask
• Updated init method implementations in MPPMask
• Fixed implementation of init methods in MPPMask
• Added MPPMask Tests
• Added iOS Image Segmenter Result
• Added iOS Image Segmenter Options
• Updated image segmenter delegate method to be required
• Added copying of running mode in NSCopying implementation in iOS tasks
• Added iOS Image Segmenter Options Helpers
• Added Image Segmenter Result Helpers

Javascript

• Add CommonJS bundle for MediaPipe Tasks
• Use .mjs for ESM Modules and use .cjs for CommonJS
• Add "exports" field definitions to package.json

Model Maker changes

• Use GFile for internal file systems.
• 1. Model maker core classifier change _metric_function field to _metric_functions in order to support having multiple metrics.
• Add a face alignment preprocessor to face stylizer.
• Support ExBert training and option to select between AdamW and LAMB optimizers for BertClassifier
• Add MobileNetV2_I320 and MobileNetMultiHWAVG_I384 to support larger input image sizes.

MediaPipe Dependencies

• Update WASM files for 0.10.2 release

Major Features and Improvements

iOS

• Published MediaPipeTasksText and MediaPipeTasksVision CocoaPods at version 0.10.1-alpha-2
• Add FaceDetector iOS API
• Add Gesture Recognizer iOS API

Web

• Add iOS support for GPU processing for Segmentation Tasks
• Add .close() method to ImageSegmenterResult/InteractiveSegmenterResult/PoseLandmarkerResult
• Add quality scores to Segmenter tasks
• Make FaceLandmarker result non-optional

Bug Fixes and Other Changes

Android

• Remove unused MediaPipe Tasks Android sample

iOS

• Added validation of C++ image classification result packet in MPPImageClassifierResult+Helpers.mm
• Fixed deps in iOS task BUILD file
• Reverted addition of flow limiter calculator in image classifier iOS
• Added delegates in iOS gesture recognizer options
• Added MPPGestureRecognizerOptionsHelpers, MPPGestureRecognizerResultHelpers, MPPGestureRecognizer header
• Updated the vision task runner to split the method that creates normalized rect based on ROI
• Added C++ utils for parsing protos from text files for iOS tests
• Added hand landmarker result, hand landmarker options, hand landmarker options helpers
• Add FaceLandmarkerOptions and FaceLandmarker Result API
• Added utils of containers and core to MPPTaskCommon to avoid warnings in xcode
• Updated error tests to use XCTAssertEqualObjects

Javascript

• Update WASM files for 0.10.1 release

Framework and Core Calculator Improvements

Bug Fixes and Other Changes

• Added clearing of all graph options protos in MPPGestureRecognizerOptions Helpers, support to set delegates in MPPBaseOptions
• Added method to create unique dispatch queue names in MPPVisionTaskRunner
• Updated MPPImageClassifier to use delegates instead of completion blocks for callback
• Updated documentation
• Updated time out for image classifier async tests
• Updated time out for object detector
• Added flow limiter calculator in MediaPipeTasksCommon
• Added clearing of all graph options protos in MPPGestureRecognizerOptions Helpers
• Update base_options.py
• Update Dockerfile
• Add some helpful error messages in case GL texture creation fails
• Updated Image classifier result to return empty results if packet can't be validated
• Updated MPPObjectDetectorResult Helpers to return empty result instead of nil
• Add needed enum type for choose fuse pipeline
• Added C++ utils for parsing protos from text files for iOS tests
• Updated face detector to use new methods from vision task runner
• Updated variable names in MPPHandLandmarkerOptionsHelpers
• Add MultiLandmarksSmoothingCalculator
• Add MP_DISABLE_GPU to .so target
• Updated CVPixelBuffer to support pixel format type of 32RGBA
• Added support to set delegates in MPPBaseOptions

MediaPipe Dependencies

• Removed opencv dependency from MPPVIsionTaskRunner
• Update MediaPipe to RE2 release 2023-06-01

Major Features and Improvements

• Released MediaPipe Solutions APIs for Java, Python and Web that offer advanced end-to-end solutions for end-to-end on-device ML.

Bug Fixes and Other Changes

Bazel changes

• Updated bazelrc with required config

Framework and core calculator improvements

• Added Language Detector Python API and fixed a typo in Interactive Segmenter Options' docstring, Update CalculatorOptions to encourage proto3 options
• Updated roi not allowed check in ios vision task runner
• Updated normalized rect calculation for some angles in MPPVisionTaskRunner
• Added shell script for building cocoapods archive
• Added more pose landmarker tests and updated face landmarker tests to cover all the results
• Added Language Detector Python API and fixed a typo in Interactive Segmenter Options' docstring
• Add nullable annotation to AudioDataProducer#setAudioConsumer
• Add a default_applicable_licenses to model_maker/python/vision/core
• Added podspec for CommonObjects and Vision tasks
• Add customizable face stylizer module in MediaPipe model maker
• Add custom metadata for object detection model with out-of-graph nms
• Update MPImage to use containers
• Update the face stylizer config to match the latest encoder and detector config
• Add nose in facemesh drawing
• Added config for fat simulator builds
• Added http_archive to download opencv sources
• Added config settings to select building iOS xcframework from source for certain configs
• Updated BUILD files to use the open sourced Language Detector model
• Add the TFLite conversion API to BlazeFaceStylizer in model maker
• Add the "FACE_ALIGNMENT" output stream to the face stylizer graph
• Add an extra op to rescale face stylizer generation output from [-1, 1] to [0, 1]
• Add TransformerParameters proto
• Updated docuemntation of MPPObjectDetector
• Added hash implementation for iOS normalized keypoint
• Updated wait time for object detector tests
• Updated pixel format types in object detector
• Added flow limiter calculator and conditionally selected xcframework in iOS framework targets
• Added conditional building of opencv xc framework to test targets
• Update CalculatorOptions to encourage proto3 options
• Add support for single-channel images to MPImage

MediaPipe solutions update

Android

• Move Java Connections arrays to Task class

iOS

• Updated roi not allowed check in iOS vision task runner
• Removed roi apis from iOS object detector
• Added iOS Object Detector Objective D tests
• Removed detect in image with region of interest api from iOS Object Detector
• Updated iOS tests to reflect the new orientation calculation
• Updated iOS Image Classifier to reflect new calculation for normalized rect
• Updated build rules for iOS frameworks to duplicate symbols
• Updated iOS cocoapods build script
• Updated iOS framework names
• Added build file for iOS opencv from sources
• Updated iOS object detector to use delegates instead of callbacks for async calls
• Added hash implementation for iOS normalized keypoint
• Added flow limiter calculator and conditionally selected xcframework in iOS framework targets
• Updated deps names in iOS test targets
• Added iOS task text cocoapods podspec
• Added targets for iOS text frameworks
• Added method for creating unique dispatch queue names in MPPVisionTaskRunner

Javascript

• Add scribble support to InteractiveSegmenter Web API
• Update WASM files for Alpha 14
• Add .close() method to ImageSegmenterResult/InteractiveSegmenterResult/PoseLandmarkerResult
• Update FaceStylizer, ImageSegmenter, InteractiveSegmenter, PoseLandmarker to return MPImage

Python

• Added the PoseLandmarker Python API and a simple test
• Populate labels using model metadata for the ImageSegmenter Python API
• Added the Face Aligner Python API
• Expose PoseLandmarker as a public MediaPipe Tasks Python API
• Expose FaceAligner and LanguageDetector to be public MediaPipe Tasks Python API
• Add image_segmenter_metadata_schema and object_detector_metadata_schema python files to the mediapipe python wheels
• Add HAND_CONNECTIONS to HandLandmarker and GestureRecognizer

MediaPipe Dependencies

• Aded version of dependency to podspec template
• Updated common dependencies to link in helpers