Project import generated by Copybara.

GitOrigin-RevId: 1e13be30e2c6838d4a2ff768a39c414bc80534bb

MANIFEST.in

@@ -7,14 +7,4 @@ include MANIFEST.in
 include README.md
 include requirements.txt
 
-recursive-include mediapipe/modules *.tflite *.txt *.binarypb
+recursive-include mediapipe/modules *.txt
-exclude mediapipe/modules/face_detection/face_detection_full_range.tflite
-exclude mediapipe/modules/objectron/object_detection_3d_chair_1stage.tflite
-exclude mediapipe/modules/objectron/object_detection_3d_sneakers_1stage.tflite
-exclude mediapipe/modules/objectron/object_detection_3d_sneakers.tflite
-exclude mediapipe/modules/objectron/object_detection_3d_chair.tflite
-exclude mediapipe/modules/objectron/object_detection_3d_camera.tflite
-exclude mediapipe/modules/objectron/object_detection_3d_cup.tflite
-exclude mediapipe/modules/objectron/object_detection_ssd_mobilenetv2_oidv4_fp16.tflite
-exclude mediapipe/modules/pose_landmark/pose_landmark_lite.tflite
-exclude mediapipe/modules/pose_landmark/pose_landmark_heavy.tflite

README.md

@@ -4,7 +4,7 @@ title: Home
 nav_order: 1
 ---
 
-![MediaPipe](docs/images/mediapipe_small.png)
+![MediaPipe](https://mediapipe.dev/images/mediapipe_small.png)
 
 --------------------------------------------------------------------------------
 
@@ -13,21 +13,21 @@ nav_order: 1
 [MediaPipe](https://google.github.io/mediapipe/) offers cross-platform, customizable
 ML solutions for live and streaming media.
 
-![accelerated.png](docs/images/accelerated_small.png)                                                               | ![cross_platform.png](docs/images/cross_platform_small.png)
+![accelerated.png](https://mediapipe.dev/images/accelerated_small.png)                                                               | ![cross_platform.png](https://mediapipe.dev/images/cross_platform_small.png)
 :------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------:
 ***End-to-End acceleration***: *Built-in fast ML inference and processing accelerated even on common hardware* | ***Build once, deploy anywhere***: *Unified solution works across Android, iOS, desktop/cloud, web and IoT*
-![ready_to_use.png](docs/images/ready_to_use_small.png)                                                             | ![open_source.png](docs/images/open_source_small.png)
+![ready_to_use.png](https://mediapipe.dev/images/ready_to_use_small.png)                                                             | ![open_source.png](https://mediapipe.dev/images/open_source_small.png)
 ***Ready-to-use solutions***: *Cutting-edge ML solutions demonstrating full power of the framework*            | ***Free and open source***: *Framework and solutions both under Apache 2.0, fully extensible and customizable*
 
 ## ML solutions in MediaPipe
 
 Face Detection                                                                                                                 | Face Mesh                                                                                                       | Iris                                                                                                      | Hands                                                                                                      | Pose                                                                                                      | Holistic
 :----------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------: | :------:
-[![face_detection](docs/images/mobile/face_detection_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/face_detection) | [![face_mesh](docs/images/mobile/face_mesh_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/face_mesh) | [![iris](docs/images/mobile/iris_tracking_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/iris) | [![hand](docs/images/mobile/hand_tracking_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/hands) | [![pose](docs/images/mobile/pose_tracking_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/pose) | [![hair_segmentation](docs/images/mobile/holistic_tracking_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/holistic)
+[![face_detection](https://mediapipe.dev/images/mobile/face_detection_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/face_detection) | [![face_mesh](https://mediapipe.dev/images/mobile/face_mesh_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/face_mesh) | [![iris](https://mediapipe.dev/images/mobile/iris_tracking_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/iris) | [![hand](https://mediapipe.dev/images/mobile/hand_tracking_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/hands) | [![pose](https://mediapipe.dev/images/mobile/pose_tracking_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/pose) | [![hair_segmentation](https://mediapipe.dev/images/mobile/holistic_tracking_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/holistic)
 
 Hair Segmentation                                                                                                                       | Object Detection                                                                                                                     | Box Tracking                                                                                                                | Instant Motion Tracking                                                                                                                               | Objectron                                                                                                             | KNIFT
 :-------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------: | :---:
-[![hair_segmentation](docs/images/mobile/hair_segmentation_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/hair_segmentation) | [![object_detection](docs/images/mobile/object_detection_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/object_detection) | [![box_tracking](docs/images/mobile/object_tracking_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/box_tracking) | [![instant_motion_tracking](docs/images/mobile/instant_motion_tracking_android_small.gif)](https://google.github.io/mediapipe/solutions/instant_motion_tracking) | [![objectron](docs/images/mobile/objectron_chair_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/objectron) | [![knift](docs/images/mobile/template_matching_android_cpu_small.gif)](https://google.github.io/mediapipe/solutions/knift)
+[![hair_segmentation](https://mediapipe.dev/images/mobile/hair_segmentation_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/hair_segmentation) | [![object_detection](https://mediapipe.dev/images/mobile/object_detection_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/object_detection) | [![box_tracking](https://mediapipe.dev/images/mobile/object_tracking_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/box_tracking) | [![instant_motion_tracking](https://mediapipe.dev/images/mobile/instant_motion_tracking_android_small.gif)](https://google.github.io/mediapipe/solutions/instant_motion_tracking) | [![objectron](https://mediapipe.dev/images/mobile/objectron_chair_android_gpu_small.gif)](https://google.github.io/mediapipe/solutions/objectron) | [![knift](https://mediapipe.dev/images/mobile/template_matching_android_cpu_small.gif)](https://google.github.io/mediapipe/solutions/knift)
 
 <!-- []() in the first cell is needed to preserve table formatting in GitHub Pages. -->
 <!-- Whenever this table is updated, paste a copy to solutions/solutions.md. -->

WORKSPACE

@@ -2,6 +2,12 @@ workspace(name = "mediapipe")
 
 load("@bazel_tools//tools/build_defs/repo:http.bzl", "http_archive")
 
+# Protobuf expects an //external:python_headers target
+bind(
+    name = "python_headers",
+    actual = "@local_config_python//:python_headers",
+)
+
 http_archive(
     name = "bazel_skylib",
     type = "tar.gz",
@@ -142,12 +148,50 @@ http_archive(
     ],
 )
 
+load("//third_party/flatbuffers:workspace.bzl", flatbuffers = "repo")
+flatbuffers()
+
 http_archive(
     name = "com_google_audio_tools",
     strip_prefix = "multichannel-audio-tools-master",
     urls = ["https://github.com/google/multichannel-audio-tools/archive/master.zip"],
 )
 
+# sentencepiece
+http_archive(
+    name = "com_google_sentencepiece",
+    strip_prefix = "sentencepiece-1.0.0",
+    sha256 = "c05901f30a1d0ed64cbcf40eba08e48894e1b0e985777217b7c9036cac631346",
+    urls = [
+        "https://github.com/google/sentencepiece/archive/1.0.0.zip",
+    ],
+    repo_mapping = {"@com_google_glog" : "@com_github_glog_glog"},
+)
+
+http_archive(
+    name = "org_tensorflow_text",
+    sha256 = "f64647276f7288d1b1fe4c89581d51404d0ce4ae97f2bcc4c19bd667549adca8",
+    strip_prefix = "text-2.2.0",
+    urls = [
+        "https://github.com/tensorflow/text/archive/v2.2.0.zip",
+    ],
+    patches = [
+        "//third_party:tensorflow_text_remove_tf_deps.diff",
+        "//third_party:tensorflow_text_a0f49e63.diff",
+    ],
+    patch_args = ["-p1"],
+    repo_mapping = {"@com_google_re2": "@com_googlesource_code_re2"},
+)
+
+http_archive(
+    name = "com_googlesource_code_re2",
+    sha256 = "e06b718c129f4019d6e7aa8b7631bee38d3d450dd980246bfaf493eb7db67868",
+    strip_prefix = "re2-fe4a310131c37f9a7e7f7816fa6ce2a8b27d65a8",
+    urls = [
+        "https://github.com/google/re2/archive/fe4a310131c37f9a7e7f7816fa6ce2a8b27d65a8.tar.gz",
+    ],
+)
+
 # 2020-07-09
 http_archive(
     name = "pybind11_bazel",
@@ -167,6 +211,15 @@ http_archive(
     build_file = "@pybind11_bazel//:pybind11.BUILD",
 )
 
+http_archive(
+    name = "pybind11_protobuf",
+    sha256 = "baa1f53568283630a5055c85f0898b8810f7a6431bd01bbaedd32b4c1defbcb1",
+    strip_prefix = "pybind11_protobuf-3594106f2df3d725e65015ffb4c7886d6eeee683",
+    urls = [
+        "https://github.com/pybind/pybind11_protobuf/archive/3594106f2df3d725e65015ffb4c7886d6eeee683.tar.gz",
+    ],
+)
+
 # Point to the commit that deprecates the usage of Eigen::MappedSparseMatrix.
 http_archive(
     name = "ceres_solver",
@@ -377,10 +430,29 @@ http_archive(
     ],
 )
 
-# Tensorflow repo should always go after the other external dependencies.
+# Load Zlib before initializing TensorFlow to guarantee that the target
-# 2022-02-15
+# @zlib//:mini_zlib is available
-_TENSORFLOW_GIT_COMMIT = "a3419acc751dfc19caf4d34a1594e1f76810ec58"
+http_archive(
-_TENSORFLOW_SHA256 = "b95b2a83632d4055742ae1a2dcc96b45da6c12a339462dbc76c8bca505308e3a"
+    name = "zlib",
+    build_file = "//third_party:zlib.BUILD",
+    sha256 = "c3e5e9fdd5004dcb542feda5ee4f0ff0744628baf8ed2dd5d66f8ca1197cb1a1",
+    strip_prefix = "zlib-1.2.11",
+    urls = [
+        "http://mirror.bazel.build/zlib.net/fossils/zlib-1.2.11.tar.gz",
+        "http://zlib.net/fossils/zlib-1.2.11.tar.gz",  # 2017-01-15
+    ],
+    patches = [
+        "@//third_party:zlib.diff",
+    ],
+    patch_args = [
+        "-p1",
+    ],
+)
+
+# TensorFlow repo should always go after the other external dependencies.
+# TF on 2022-08-10.
+_TENSORFLOW_GIT_COMMIT = "af1d5bc4fbb66d9e6cc1cf89503014a99233583b"
+_TENSORFLOW_SHA256 = "f85a5443264fc58a12d136ca6a30774b5bc25ceaf7d114d97f252351b3c3a2cb"
 http_archive(
     name = "org_tensorflow",
     urls = [
@@ -417,3 +489,6 @@ libedgetpu_dependencies()
 
 load("@coral_crosstool//:configure.bzl", "cc_crosstool")
 cc_crosstool(name = "crosstool")
+
+load("//third_party:external_files.bzl", "external_files")
+external_files()

docs/_config.yml

@@ -20,7 +20,7 @@ aux_links:
     - "//github.com/google/mediapipe"
 
 # Footer content appears at the bottom of every page's main content
-footer_content: "&copy; 2020 GOOGLE LLC | <a href=\"https://policies.google.com/privacy\">PRIVACY POLICY</a> | <a href=\"https://policies.google.com/terms\">TERMS OF SERVICE</a>"
+footer_content: "&copy; GOOGLE LLC | <a href=\"https://policies.google.com/privacy\">PRIVACY POLICY</a> | <a href=\"https://policies.google.com/terms\">TERMS OF SERVICE</a>"
 
 # Color scheme currently only supports "dark", "light"/nil (default), or a custom scheme that you define
 color_scheme: mediapipe

docs/framework_concepts/calculators.md

@@ -133,7 +133,7 @@ write outputs. After Close returns, the calculator is destroyed.
 Calculators with no inputs are referred to as sources. A source calculator
 continues to have `Process()` called as long as it returns an `Ok` status. A
 source calculator indicates that it is exhausted by returning a stop status
-(i.e. MediaPipe::tool::StatusStop).
+(i.e. [`mediaPipe::tool::StatusStop()`](https://github.com/google/mediapipe/tree/master/mediapipe/framework/tool/status_util.cc).).
 
 ## Identifying inputs and outputs
 
@@ -459,6 +459,6 @@ node {
 The diagram below shows how the `PacketClonerCalculator` defines its output
 packets (bottom) based on its series of input packets (top).
 
-![Graph using PacketClonerCalculator](../images/packet_cloner_calculator.png)  |
+![Graph using PacketClonerCalculator](https://mediapipe.dev/images/packet_cloner_calculator.png)  |
 :--------------------------------------------------------------------------: |
 *Each time it receives a packet on its TICK input stream, the PacketClonerCalculator outputs the most recent packet from each of its input streams. The sequence of output packets (bottom) is determined by the sequence of input packets (top) and their timestamps. The timestamps are shown along the right side of the diagram.* |

docs/framework_concepts/gpu.md

@@ -149,7 +149,7 @@ When possible, these calculators use platform-specific functionality to share da
 
 The below diagram shows the data flow in a mobile application that captures video from the camera, runs it through a MediaPipe graph, and renders the output on the screen in real time. The dashed line indicates which parts are inside the MediaPipe graph proper. This application runs a Canny edge-detection filter on the CPU using OpenCV, and overlays it on top of the original video using the GPU.
 
-![How GPU calculators interact](../images/gpu_example_graph.png)
+![How GPU calculators interact](https://mediapipe.dev/images/gpu_example_graph.png)
 
 Video frames from the camera are fed into the graph as `GpuBuffer` packets. The
 input stream is accessed by two calculators in parallel.

docs/framework_concepts/graphs.md

@@ -159,7 +159,7 @@ Please use the `CalculatorGraphTest.Cycle` unit test in
 below is the cyclic graph in the test. The `sum` output of the adder is the sum
 of the integers generated by the integer source calculator.
 
-![a cyclic graph that adds a stream of integers](../images/cyclic_integer_sum_graph.svg "A cyclic graph")
+![a cyclic graph that adds a stream of integers](https://mediapipe.dev/images/cyclic_integer_sum_graph.svg "A cyclic graph")
 
 This simple graph illustrates all the issues in supporting cyclic graphs.
 

docs/getting_started/android_archive_library.md

@@ -102,7 +102,7 @@ each project.
     /path/to/your/app/libs/
     ```
 
-    ![Screenshot](../images/mobile/aar_location.png)
+    ![Screenshot](https://mediapipe.dev/images/mobile/aar_location.png)
 
 3.  Make app/src/main/assets and copy assets (graph, model, and etc) into
     app/src/main/assets.
@@ -120,7 +120,7 @@ each project.
     cp mediapipe/modules/face_detection/face_detection_short_range.tflite /path/to/your/app/src/main/assets/
     ```
 
-    ![Screenshot](../images/mobile/assets_location.png)
+    ![Screenshot](https://mediapipe.dev/images/mobile/assets_location.png)
 
 4.  Modify app/build.gradle to add MediaPipe dependencies and MediaPipe AAR.
 

docs/getting_started/android_solutions.md

@@ -55,18 +55,18 @@ To build these apps:
 
 2.  Import mediapipe/examples/android/solutions directory into Android Studio.
 
-    ![Screenshot](../images/import_mp_android_studio_project.png)
+    ![Screenshot](https://mediapipe.dev/images/import_mp_android_studio_project.png)
 
 3.  For Windows users, run `create_win_symlinks.bat` as administrator to create
     res directory symlinks.
 
-    ![Screenshot](../images/run_create_win_symlinks.png)
+    ![Screenshot](https://mediapipe.dev/images/run_create_win_symlinks.png)
 
 4.  Select "File" -> "Sync Project with Gradle Files" to sync project.
 
 5.  Run solution example app in Android Studio.
 
-    ![Screenshot](../images/run_android_solution_app.png)
+    ![Screenshot](https://mediapipe.dev/images/run_android_solution_app.png)
 
 6.  (Optional) Run solutions on CPU.
 

docs/getting_started/hello_world_android.md

@@ -27,7 +27,7 @@ graph on Android.
 A simple camera app for real-time Sobel edge detection applied to a live video
 stream on an Android device.
 
-![edge_detection_android_gpu_gif](../images/mobile/edge_detection_android_gpu.gif)
+![edge_detection_android_gpu_gif](https://mediapipe.dev/images/mobile/edge_detection_android_gpu.gif)
 
 ## Setup
 
@@ -69,7 +69,7 @@ node: {
 
 A visualization of the graph is shown below:
 
-![edge_detection_mobile_gpu](../images/mobile/edge_detection_mobile_gpu.png)
+![edge_detection_mobile_gpu](https://mediapipe.dev/images/mobile/edge_detection_mobile_gpu.png)
 
 This graph has a single input stream named `input_video` for all incoming frames
 that will be provided by your device's camera.
@@ -260,7 +260,7 @@ adb install bazel-bin/$APPLICATION_PATH/helloworld.apk
 Open the application on your device. It should display a screen with the text
 `Hello World!`.
 
-![bazel_hello_world_android](../images/mobile/bazel_hello_world_android.png)
+![bazel_hello_world_android](https://mediapipe.dev/images/mobile/bazel_hello_world_android.png)
 
 ## Using the camera via `CameraX`
 
@@ -377,7 +377,7 @@ Add the following line in the `$APPLICATION_PATH/res/values/strings.xml` file:
 When the user doesn't grant camera permission, the screen will now look like
 this:
 
-![missing_camera_permission_android](../images/mobile/missing_camera_permission_android.png)
+![missing_camera_permission_android](https://mediapipe.dev/images/mobile/missing_camera_permission_android.png)
 
 Now, we will add the [`SurfaceTexture`] and [`SurfaceView`] objects to
 `MainActivity`:
@@ -753,7 +753,7 @@ And that's it! You should now be able to successfully build and run the
 application on the device and see Sobel edge detection running on a live camera
 feed! Congrats!
 
-![edge_detection_android_gpu_gif](../images/mobile/edge_detection_android_gpu.gif)
+![edge_detection_android_gpu_gif](https://mediapipe.dev/images/mobile/edge_detection_android_gpu.gif)
 
 If you ran into any issues, please see the full code of the tutorial
 [here](https://github.com/google/mediapipe/tree/master/mediapipe/examples/android/src/java/com/google/mediapipe/apps/basic).

docs/getting_started/hello_world_cpp.md

@@ -85,7 +85,7 @@ nav_order: 1
     This graph consists of 1 graph input stream (`in`) and 1 graph output stream
     (`out`), and 2 [`PassThroughCalculator`]s connected serially.
 
-    ![hello_world graph](../images/hello_world.png)
+    ![hello_world graph](https://mediapipe.dev/images/hello_world.png)
 
 4.  Before running the graph, an `OutputStreamPoller` object is connected to the
     output stream in order to later retrieve the graph output, and a graph run

docs/getting_started/hello_world_ios.md

@@ -27,7 +27,7 @@ on iOS.
 A simple camera app for real-time Sobel edge detection applied to a live video
 stream on an iOS device.
 
-![edge_detection_ios_gpu_gif](../images/mobile/edge_detection_ios_gpu.gif)
+![edge_detection_ios_gpu_gif](https://mediapipe.dev/images/mobile/edge_detection_ios_gpu.gif)
 
 ## Setup
 
@@ -67,7 +67,7 @@ node: {
 
 A visualization of the graph is shown below:
 
-![edge_detection_mobile_gpu](../images/mobile/edge_detection_mobile_gpu.png)
+![edge_detection_mobile_gpu](https://mediapipe.dev/images/mobile/edge_detection_mobile_gpu.png)
 
 This graph has a single input stream named `input_video` for all incoming frames
 that will be provided by your device's camera.
@@ -580,7 +580,7 @@ Update the interface definition of `ViewController` with `MPPGraphDelegate`:
 And that is all! Build and run the app on your iOS device. You should see the
 results of running the edge detection graph on a live video feed. Congrats!
 
-![edge_detection_ios_gpu_gif](../images/mobile/edge_detection_ios_gpu.gif)
+![edge_detection_ios_gpu_gif](https://mediapipe.dev/images/mobile/edge_detection_ios_gpu.gif)
 
 Please note that the iOS examples now use a [common] template app. The code in
 this tutorial is used in the [common] template app. The [helloworld] app has the

docs/getting_started/python.md

@@ -113,9 +113,8 @@ Nvidia Jetson and Raspberry Pi, please read
 
     Download the latest protoc win64 zip from
     [the Protobuf GitHub repo](https://github.com/protocolbuffers/protobuf/releases),
-    unzip the file, and copy the protoc.exe executable to a preferred
+    unzip the file, and copy the protoc.exe executable to a preferred location.
-    location. Please ensure that location is added into the Path environment
+    Please ensure that location is added into the Path environment variable.
-    variable.
 
 3.  Activate a Python virtual environment.
 
@@ -131,16 +130,14 @@ Nvidia Jetson and Raspberry Pi, please read
     (mp_env)mediapipe$ pip3 install -r requirements.txt
     ```
 
-6.  Generate and install MediaPipe package.
+6.  Build and install MediaPipe package.
 
     ```bash
-    (mp_env)mediapipe$ python3 setup.py gen_protos
     (mp_env)mediapipe$ python3 setup.py install --link-opencv
     ```
 
     or
 
     ```bash
-    (mp_env)mediapipe$ python3 setup.py gen_protos
     (mp_env)mediapipe$ python3 setup.py bdist_wheel
     ```