Project import generated by Copybara.

GitOrigin-RevId: b137378673f7d66d41bcd46e4fc3a0d9ef254894
2019-10-25 14:29:15 -07:00
parent a2a63e3876
commit 259b48e082
94 changed files with 8564 additions and 398 deletions
@@ -0,0 +1,130 @@
+## MediaPipe Android Archive Library
+
+***Experimental Only***
+
+The MediaPipe Android archive library is a convenient way to use MediaPipe with
+Android Studio and Gradle. MediaPipe doesn't publish a general AAR that can be
+used by all projects. Instead, developers need to add a mediapipe_aar() target
+to generate a custom AAR file for their own projects. This is necessary in order
+to include specific resources such as MediaPipe calculators needed for each
+project.
+
+### Steps to build a MediaPipe AAR
+
+1.  Create a mediapipe_aar() target.
+
+    In the MediaPipe directory, create a new mediapipe_aar() target in a BUILD
+    file. You need to figure out what calculators are used in the graph and
+    provide the calculator dependencies to the mediapipe_aar(). For example, to
+    build an AAR for [face detection gpu](./face_detection_mobile_gpu.md), you
+    can put the following code into
+    mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example/BUILD.
+
+    ```
+    load("//mediapipe/java/com/google/mediapipe:mediapipe_aar.bzl", "mediapipe_aar")
+
+    mediapipe_aar(
+        name = "mp_face_detection_aar",
+        calculators = ["//mediapipe/graphs/face_detection:mobile_calculators"],
+    )
+    ```
+
+2.  Run the Bazel build command to generate the AAR.
+
+    ```bash
+    bazel build -c opt --fat_apk_cpu=arm64-v8a,armeabi-v7a //path/to/the/aar/build/file:aar_name
+    ```
+
+    For the face detection AAR target we made in the step 1, run:
+
+    ```bash
+    bazel build -c opt --fat_apk_cpu=arm64-v8a,armeabi-v7a \
+        //mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example:mp_face_detection_aar
+
+    # It should print:
+    # Target //mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example:mp_face_detection_aar up-to-date:
+    # bazel-bin/mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example/mp_face_detection_aar.aar
+    ```
+
+3.  (Optional) Save the AAR to your preferred location.
+
+    ```bash
+    cp bazel-bin/mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example/mp_face_detection_aar.aar
+    /absolute/path/to/your/preferred/location
+    ```
+
+### Steps to use a MediaPipe AAR in Android Studio with Gradle
+
+1.  Start Android Studio and go to your project.
+
+2.  Copy the AAR into app/libs.
+
+    ```bash
+    cp bazel-bin/mediapipe/examples/android/src/java/com/google/mediapipe/apps/aar_example/mp_face_detection_aar.aar
+    /path/to/your/app/libs/
+    ```
+
+    ![Screenshot](images/mobile/aar_location.png)
+
+3.  Make app/src/main/assets and copy assets (graph, model, and etc) into
+    app/src/main/assets.
+
+    Build the MediaPipe binary graph and copy the assets into
+    app/src/main/assets, e.g., for the face detection graph, you need to build
+    and copy
+    [the binary graph](https://github.com/google/mediapipe/blob/master/mediapipe/examples/android/src/java/com/google/mediapipe/apps/facedetectiongpu/BUILD#L41),
+    [the tflite model](https://github.com/google/mediapipe/tree/master/mediapipe/models/face_detection_front.tflite),
+    and
+    [the label map](https://github.com/google/mediapipe/blob/master/mediapipe/models/face_detection_front_labelmap.txt).
+
+    ```bash
+    bazel build -c opt mediapipe/examples/android/src/java/com/google/mediapipe/apps/facedetectiongpu:binary_graph
+    cp bazel-bin/mediapipe/examples/android/src/java/com/google/mediapipe/apps/facedetectiongpu/facedetectiongpu.binarypb /path/to/your/app/src/main/assets/
+    cp mediapipe/models/face_detection_front.tflite /path/to/your/app/src/main/assets/
+    cp mediapipe/models/face_detection_front_labelmap.txt /path/to/your/app/src/main/assets/
+    ```
+
+    ![Screenshot](images/mobile/assets_location.png)
+
+4.  Make app/src/main/jniLibs and copy OpenCV JNI libraries into
+    app/src/main/jniLibs.
+
+    MediaPipe depends on OpenCV, you will need to copy the precompiled OpenCV so
+    files into app/src/main/jniLibs. You can download the official OpenCV
+    Android SDK from
+    [here](https://github.com/opencv/opencv/releases/download/4.1.0/opencv-4.1.0-android-sdk.zip)
+    and run:
+
+    ```bash
+    cp -R ~/Downloads/OpenCV-android-sdk/sdk/native/libs/arm* /path/to/your/app/src/main/jniLibs/
+    ```
+
+    ![Screenshot](images/mobile/android_studio_opencv_location.png)
+
+5.  Modify app/build.gradle to add MediaPipe dependencies and MediaPipe AAR.
+
+    ```
+    dependencies {
+        implementation fileTree(dir: 'libs', include: ['*.jar', '*.aar'])
+        implementation 'androidx.appcompat:appcompat:1.0.2'
+        implementation 'androidx.constraintlayout:constraintlayout:1.1.3'
+        testImplementation 'junit:junit:4.12'
+        androidTestImplementation 'androidx.test.ext:junit:1.1.0'
+        androidTestImplementation 'androidx.test.espresso:espresso-core:3.1.1'
+        // MediaPipe deps
+        implementation 'com.google.flogger:flogger:0.3.1'
+        implementation 'com.google.flogger:flogger-system-backend:0.3.1'
+        implementation 'com.google.code.findbugs:jsr305:3.0.2'
+        implementation 'com.google.guava:guava:27.0.1-android'
+        implementation 'com.google.guava:guava:27.0.1-android'
+        // CameraX core library
+        def camerax_version = "1.0.0-alpha06"
+        implementation "androidx.camera:camera-core:$camerax_version"
+        implementation "androidx.camera:camera-camera2:$camerax_version"
+    }
+    ```
+
+6.  Follow our Android app examples to use MediaPipe in Android Studio for your
+    use case. If you are looking for an example, a working face detection
+    example can be found
+    [here](https://github.com/jiuqiant/mediapipe_aar_example).
@@ -96,8 +96,9 @@ using the MediaPipe C++ APIs.

 ### Feature Extration for YouTube-8M Challenge

-[Feature Extration for YouTube-8M Challenge](./youtube_8m.md) shows how to use
-MediaPipe to prepare training data for the YouTube-8M Challenge.
+[Feature Extration and Model Inference for YouTube-8M Challenge](./youtube_8m.md)
+shows how to use MediaPipe to prepare training data for the YouTube-8M Challenge
+and do the model inference with the baseline model.

 ### Preparing Data Sets with MediaSequence

@@ -36,10 +36,9 @@ $ bazel build -c opt --define MEDIAPIPE_DISABLE_GPU=1 \
 # INFO: 711 processes: 710 linux-sandbox, 1 local.
 # INFO: Build completed successfully, 734 total actions

-$ export GLOG_logtostderr=1
 # This will open up your webcam as long as it is connected and on
 # Any errors is likely due to your webcam being not accessible
-$ bazel-bin/mediapipe/examples/desktop/face_detection/face_detection_cpu \
+$ GLOG_logtostderr=1 bazel-bin/mediapipe/examples/desktop/face_detection/face_detection_cpu \
    --calculator_graph_config_file=mediapipe/graphs/face_detection/face_detection_desktop_live.pbtxt
 ```

@@ -60,11 +59,10 @@ $ bazel build -c opt --copt -DMESA_EGL_NO_X11_HEADERS \
 # INFO: 711 processes: 710 linux-sandbox, 1 local.
 # INFO: Build completed successfully, 734 total actions

-$ export GLOG_logtostderr=1
 # This will open up your webcam as long as it is connected and on
 # Any errors is likely due to your webcam being not accessible,
 # or GPU drivers not setup properly.
-$ bazel-bin/mediapipe/examples/desktop/face_detection/face_detection_gpu \
+$ GLOG_logtostderr=1 bazel-bin/mediapipe/examples/desktop/face_detection/face_detection_gpu \
    --calculator_graph_config_file=mediapipe/graphs/face_detection/face_detection_mobile_gpu.pbtxt
 ```

@@ -35,11 +35,10 @@ $ bazel build -c opt --copt -DMESA_EGL_NO_X11_HEADERS \
 #INFO: Streaming build results to: http://sponge2/37d5a184-293b-4e98-a43e-b22084db3142
 #INFO: Build completed successfully, 12210 total actions

-$ export GLOG_logtostderr=1
 # This will open up your webcam as long as it is connected and on
 # Any errors is likely due to your webcam being not accessible,
 # or GPU drivers not setup properly.
-$ bazel-bin/mediapipe/examples/desktop/hair_segmentation/hair_segmentation_gpu \
+$ GLOG_logtostderr=1 bazel-bin/mediapipe/examples/desktop/hair_segmentation/hair_segmentation_gpu \
    --calculator_graph_config_file=mediapipe/graphs/hair_segmentation/hair_segmentation_mobile_gpu.pbtxt
 ```

@@ -35,10 +35,9 @@ $ bazel build -c opt --define MEDIAPIPE_DISABLE_GPU=1 \
 #INFO: Streaming build results to: http://sponge2/360196b9-33ab-44b1-84a7-1022b5043307
 #INFO: Build completed successfully, 12517 total actions

-$ export GLOG_logtostderr=1
 # This will open up your webcam as long as it is connected and on
 # Any errors is likely due to your webcam being not accessible
-$ bazel-bin/mediapipe/examples/desktop/hand_tracking/hand_tracking_cpu \
+$ GLOG_logtostderr=1 bazel-bin/mediapipe/examples/desktop/hand_tracking/hand_tracking_cpu \
    --calculator_graph_config_file=mediapipe/graphs/hand_tracking/hand_tracking_desktop_live.pbtxt
 ```

@@ -59,11 +58,10 @@ $ bazel build -c opt --copt -DMESA_EGL_NO_X11_HEADERS \
 #INFO: Streaming build results to: http://sponge2/00c7f95f-6fbc-432d-8978-f5d361efca3b
 #INFO: Build completed successfully, 22455 total actions

-$ export GLOG_logtostderr=1
 # This will open up your webcam as long as it is connected and on
 # Any errors is likely due to your webcam being not accessible,
 # or GPU drivers not setup properly.
-$ bazel-bin/mediapipe/examples/desktop/hand_tracking/hand_tracking_gpu \
+$ GLOG_logtostderr=1 bazel-bin/mediapipe/examples/desktop/hand_tracking/hand_tracking_gpu \
    --calculator_graph_config_file=mediapipe/graphs/hand_tracking/hand_tracking_mobile.pbtxt
 ```

@@ -24,7 +24,8 @@ Choose your operating system:
 To build and run Android apps:

 -   [Setting up Android SDK and NDK](#setting-up-android-sdk-and-ndk)
-   [Setting up Android Studio with MediaPipe](#setting-up-android-studio-with-mediapipe)
+-   [Using MediaPipe with Gradle](#using-mediapipe-with-gradle)
+-   [Using MediaPipe with Bazel](#using-mediapipe-with-bazel)

 To build and run iOS apps:

@@ -41,19 +42,11 @@ To build and run iOS apps:
    $ cd mediapipe
    ```

-2.  Install Bazel (0.24.1 and above required).
+2.  Install Bazel (version between 0.24.1 and 0.29.1).

-    Option 1. Use package manager tool to install the latest version of Bazel.
-
-    ```bash
-    $ sudo apt-get install bazel
-
-    # Run 'bazel version' to check version of bazel installed
-    ```
-
-    Option 2. Follow Bazel's
+    Follow the official
    [documentation](https://docs.bazel.build/versions/master/install-ubuntu.html)
-    to install any version of Bazel manually.
+    to install Bazel manually. Note that MediaPipe doesn't support Bazel 1.0.0+ yet.

 3.  Install OpenCV and FFmpeg.

@@ -75,10 +68,10 @@ To build and run iOS apps:
    [documentation](https://docs.opencv.org/3.4.6/d7/d9f/tutorial_linux_install.html)
    to manually build OpenCV from source code.

-    Note: You may need to modify [`WORKSAPCE`] and [`opencv_linux.BUILD`] to
+    Note: You may need to modify [`WORKSPACE`] and [`opencv_linux.BUILD`] to
    point MediaPipe to your own OpenCV libraries, e.g., if OpenCV 4 is installed
    in "/usr/local/", you need to update the "linux_opencv" new_local_repository
-    rule in [`WORKSAPCE`] and "opencv" cc_library rule in [`opencv_linux.BUILD`]
+    rule in [`WORKSPACE`] and "opencv" cc_library rule in [`opencv_linux.BUILD`]
    like the following:

    ```bash
@@ -159,11 +152,11 @@ To build and run iOS apps:
    $ cd mediapipe
    ```

-2.  Install Bazel (0.24.1 and above required).
+2.  Install Bazel (version between 0.24.1 and 0.29.1).

-    Follow Bazel's
+    Follow the official
    [documentation](https://docs.bazel.build/versions/master/install-redhat.html)
-    to install Bazel manually.
+    to install Bazel manually. Note that MediaPipe doesn't support Bazel 1.0.0+ yet.

 3.  Install OpenCV.

@@ -178,10 +171,10 @@ To build and run iOS apps:

    Option 2. Build OpenCV from source code.

-    Note: You may need to modify [`WORKSAPCE`] and [`opencv_linux.BUILD`] to
+    Note: You may need to modify [`WORKSPACE`] and [`opencv_linux.BUILD`] to
    point MediaPipe to your own OpenCV libraries, e.g., if OpenCV 4 is installed
    in "/usr/local/", you need to update the "linux_opencv" new_local_repository
-    rule in [`WORKSAPCE`] and "opencv" cc_library rule in [`opencv_linux.BUILD`]
+    rule in [`WORKSPACE`] and "opencv" cc_library rule in [`opencv_linux.BUILD`]
    like the following:

    ```bash
@@ -237,7 +230,7 @@ To build and run iOS apps:

    *   Install [Homebrew](https://brew.sh).
    *   Install [Xcode](https://developer.apple.com/xcode/) and its Command Line
-        Tools.
+        Tools by `xcode-select install`.

 2.  Checkout MediaPipe repository.

@@ -247,19 +240,24 @@ To build and run iOS apps:
    $ cd mediapipe
    ```

-3.  Install Bazel (0.24.1 and above required).
+3.  Install Bazel (version between 0.24.1 and 0.29.1).

-    Option 1. Use package manager tool to install the latest version of Bazel.
+     Option 1. Use package manager tool to install Bazel 0.29.1

    ```bash
-    $ brew install bazel
+    # If Bazel 1.0.0+ was installed.
+    $ brew uninstall bazel
+
+    # Install Bazel 0.29.1
+    $ brew install https://raw.githubusercontent.com/bazelbuild/homebrew-tap/223ffb570c21c0a2af251afc6df9dec0214c6e74/Formula/bazel.rb
+    $ brew link bazel

    # Run 'bazel version' to check version of bazel installed
    ```

-    Option 2. Follow Bazel's
+    Option 2. Follow the official
    [documentation](https://docs.bazel.build/versions/master/install-os-x.html#install-with-installer-mac-os-x)
-    to install any version of Bazel manually.
+    to install Bazel manually. Note that MediaPipe doesn't support Bazel 1.0.0+ yet.

 4.  Install OpenCV and FFmpeg.

@@ -281,7 +279,7 @@ To build and run iOS apps:
    $ port install opencv
    ```

-    Note: when using MacPorts, please edit the [`WORKSAPCE`],
+    Note: when using MacPorts, please edit the [`WORKSPACE`],
    [`opencv_macos.BUILD`], and [`ffmpeg_macos.BUILD`] files like the following:

    ```bash
@@ -419,10 +417,10 @@ To build and run iOS apps:
    [documentation](https://docs.opencv.org/3.4.6/d7/d9f/tutorial_linux_install.html)
    to manually build OpenCV from source code.

-    Note: You may need to modify [`WORKSAPCE`] and [`opencv_linux.BUILD`] to
+    Note: You may need to modify [`WORKSPACE`] and [`opencv_linux.BUILD`] to
    point MediaPipe to your own OpenCV libraries, e.g., if OpenCV 4 is installed
    in "/usr/local/", you need to update the "linux_opencv" new_local_repository
-    rule in [`WORKSAPCE`] and "opencv" cc_library rule in [`opencv_linux.BUILD`]
+    rule in [`WORKSPACE`] and "opencv" cc_library rule in [`opencv_linux.BUILD`]
    like the following:

    ```bash
@@ -589,10 +587,20 @@ Please verify all the necessary packages are installed.
 *   Android SDK Tools 26.1.1
 *   Android NDK 17c or above

-### Setting up Android Studio with MediaPipe
+### Using MediaPipe with Gradle

-The steps below use Android Studio 3.5 to build and install a MediaPipe example
-app.
+MediaPipe can be used within an existing project, such as a Gradle project,
+using the MediaPipe AAR target defined in mediapipe_aar.bzl. Please see the
+separate [MediaPipe Android Archive Library](./android_archive_library.md)
+documentation.
+
+### Using MediaPipe with Bazel
+
+The MediaPipe project can be imported to Android Studio using the Bazel plugins.
+This allows the MediaPipe examples and demos to be built and modified in Android
+Studio. To incorporate MediaPipe into an existing Android Studio project, see:
+"Using MediaPipe with Gradle". The steps below use Android Studio 3.5 to build
+and install a MediaPipe example app.

 1.  Install and launch Android Studio 3.5.

@@ -682,7 +690,7 @@ app.
    *   Press the `[+]` button to add the new configuration.
    *   Select `Run` to run the example app on the connected Android device.

-[`WORKSAPCE`]: https://github.com/google/mediapipe/tree/master/WORKSPACE
+[`WORKSPACE`]: https://github.com/google/mediapipe/tree/master/WORKSPACE
 [`opencv_linux.BUILD`]: https://github.com/google/mediapipe/tree/master/third_party/opencv_linux.BUILD
 [`opencv_macos.BUILD`]: https://github.com/google/mediapipe/tree/master/third_party/opencv_macos.BUILD
 [`ffmpeg_macos.BUILD`]:https://github.com/google/mediapipe/tree/master/third_party/ffmpeg_macos.BUILD
@@ -35,10 +35,9 @@ $ bazel build -c opt \
 # INFO: 2675 processes: 2673 linux-sandbox, 2 local.
 # INFO: Build completed successfully, 2807 total actions

-$ export GLOG_logtostderr=1
 # Replace <input video path> and <output video path>.
 # You can find a test video in mediapipe/examples/desktop/object_detection.
-$ bazel-bin/mediapipe/examples/desktop/object_detection/object_detection_tensorflow \
+$ GLOG_logtostderr=1 bazel-bin/mediapipe/examples/desktop/object_detection/object_detection_tensorflow \
  --calculator_graph_config_file=mediapipe/graphs/object_detection/object_detection_desktop_tensorflow_graph.pbtxt \
  --input_side_packets=input_video_path=<input video path>,output_video_path=<output video path>
 ```
@@ -200,10 +199,9 @@ $ bazel build -c opt --define MEDIAPIPE_DISABLE_GPU=1 \
 # INFO: 711 processes: 710 linux-sandbox, 1 local.
 # INFO: Build completed successfully, 734 total actions

-$ export GLOG_logtostderr=1
 # Replace <input video path> and <output video path>.
 # You can find a test video in mediapipe/examples/desktop/object_detection.
-$ bazel-bin/mediapipe/examples/desktop/object_detection/object_detection_tflite \
+$ GLOG_logtostderr=1 bazel-bin/mediapipe/examples/desktop/object_detection/object_detection_tflite \
    --calculator_graph_config_file=mediapipe/graphs/object_detection/object_detection_desktop_tflite_graph.pbtxt \
    --input_side_packets=input_video_path=<input video path>,output_video_path=<output video path>
 ```
@@ -224,10 +222,9 @@ $ bazel build -c opt --define MEDIAPIPE_DISABLE_GPU=1 \
 #INFO: Streaming build results to: http://sponge2/1824d4cc-ba63-4350-bdc0-aacbd45b902b
 #INFO: Build completed successfully, 12154 total actions

-$ export GLOG_logtostderr=1
 # This will open up your webcam as long as it is connected and on
 # Any errors is likely due to your webcam being not accessible
-$ bazel-bin/mediapipe/examples/desktop/object_detection/object_detection_cpu \
+$ GLOG_logtostderr=1 bazel-bin/mediapipe/examples/desktop/object_detection/object_detection_cpu \
    --calculator_graph_config_file=mediapipe/graphs/object_detection/object_detection_desktop_live.pbtxt
 ```

@@ -1,9 +1,11 @@
-## Extracting Video Features for YouTube-8M Challenge
+# Feature Extration and Model Inference for YouTube-8M Challenge

 MediaPipe is a useful and general framework for media processing that can assist
 with research, development, and deployment of ML models. This example focuses on
-model development by demonstrating how to prepare training data for the
-YouTube-8M Challenge.
+model development by demonstrating how to prepare training data and do model
+inference for the YouTube-8M Challenge.
+
+## Extracting Video Features for YouTube-8M Challenge

 [Youtube-8M Challenge](https://www.kaggle.com/c/youtube8m-2019) is an annual
 video classification challenge hosted by Google. Over the last two years, the
@@ -29,14 +31,14 @@ videos.

 ### Steps to run the YouTube-8M feature extraction graph

-1.  Checkout the mediapipe repository
+1.  Checkout the mediapipe repository.

    ```bash
    git clone https://github.com/google/mediapipe.git
    cd mediapipe
    ```

-2.  Download the PCA and model data
+2.  Download the PCA and model data.

    ```bash
    mkdir /tmp/mediapipe
@@ -49,7 +51,7 @@ videos.
    tar -xvf /tmp/mediapipe/inception-2015-12-05.tgz
    ```

-3.  Get the VGGish frozen graph
+3.  Get the VGGish frozen graph.

    Note: To run step 3 and step 4, you must have Python 2.7 or 3.5+ installed
    with the TensorFlow 1.14+ package installed.
@@ -60,24 +62,103 @@ videos.
    python -m mediapipe.examples.desktop.youtube8m.generate_vggish_frozen_graph
    ```

-4.  Generate a MediaSequence metadata from the input video
+4.  Generate a MediaSequence metadata from the input video.

    Note: the output file is /tmp/mediapipe/metadata.tfrecord

    ```bash
+    # change clip_end_time_sec to match the length of your video.
    python -m mediapipe.examples.desktop.youtube8m.generate_input_sequence_example \
-      --path_to_input_video=/absolute/path/to/the/local/video/file
+      --path_to_input_video=/absolute/path/to/the/local/video/file \
+      --clip_end_time_sec=120
    ```

-5.  Run the MediaPipe binary to extract the features
+5.  Run the MediaPipe binary to extract the features.

    ```bash
    bazel build -c opt \
      --define MEDIAPIPE_DISABLE_GPU=1 --define no_aws_support=true \
      mediapipe/examples/desktop/youtube8m:extract_yt8m_features

-    ./bazel-bin/mediapipe/examples/desktop/youtube8m/extract_yt8m_features
+    GLOG_logtostderr=1 bazel-bin/mediapipe/examples/desktop/youtube8m/extract_yt8m_features \
      --calculator_graph_config_file=mediapipe/graphs/youtube8m/feature_extraction.pbtxt \
      --input_side_packets=input_sequence_example=/tmp/mediapipe/metadata.tfrecord  \
      --output_side_packets=output_sequence_example=/tmp/mediapipe/output.tfrecord
    ```
+
+## Model Inference for YouTube-8M Challenge
+
+MediaPipe can help you do model inference for YouTube-8M Challenge with both
+local videos and the YouTube-8M dataset. To visualize
+[the graph for local videos](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/youtube8m/local_video_model_inference.pbtxt)
+and
+[the graph for the YouTube-8M dataset](https://github.com/google/mediapipe/tree/master/mediapipe/graphs/youtube8m/yt8m_dataset_model_inference.pbtxt),
+copy the text specification of the graph and paste it into
+[MediaPipe Visualizer](https://viz.mediapipe.dev/). We use the baseline model
+[(model card)](https://drive.google.com/file/d/1xTCi9-Nm9dt2KIk8WR0dDFrIssWawyXy/view)
+in our example. But, the model inference pipeline is highly customizable. You
+are welcome to add new calculators or use your own machine learning models to do
+the inference for both local videos and the dataset
+
+### Steps to run the YouTube-8M model inference graph with Web Interface
+
+1.  Copy the baseline model
+    [(model card)](https://drive.google.com/file/d/1xTCi9-Nm9dt2KIk8WR0dDFrIssWawyXy/view)
+    to local.
+
+    ```bash
+    curl -o /tmp/mediapipe/yt8m_baseline_saved_model.tar.gz data.yt8m.org/models/baseline/saved_model.tar.gz
+
+    tar -xvf /tmp/mediapipe/yt8m_baseline_saved_model.tar.gz -C /tmp/mediapipe
+    ```
+
+2.  Build the inference binary.
+
+    ```bash
+    bazel build -c opt --define='MEDIAPIPE_DISABLE_GPU=1' \
+      mediapipe/examples/desktop/youtube8m:model_inference
+    ```
+
+3.  Run the python web server.
+
+    Note: pip install absl-py
+
+    ```bash
+    python mediapipe/examples/desktop/youtube8m/viewer/server.py --root `pwd`
+    ```
+
+    Navigate to localhost:8008 in a web browser.
+    [Here](https://drive.google.com/file/d/19GSvdAAuAlACpBhHOaqMWZ_9p8bLUYKh/view?usp=sharing)
+    is a demo video showing the steps to use this web application. Also please
+    read
+    [youtube8m/README.md](https://github.com/google/mediapipe/tree/master/mediapipe/examples/desktop/youtube8m/README.md)
+    if you prefer to run the underlying model_inference binary in command line.
+
+### Steps to run the YouTube-8M model inference graph with a local video
+
+1.  Make sure you have the output tfrecord from the feature extraction pipeline.
+
+2.  Copy the baseline model
+    [(model card)](https://drive.google.com/file/d/1xTCi9-Nm9dt2KIk8WR0dDFrIssWawyXy/view)
+    to local.
+
+    ```bash
+    curl -o /tmp/mediapipe/yt8m_baseline_saved_model.tar.gz data.yt8m.org/models/baseline/saved_model.tar.gz
+
+    tar -xvf /tmp/mediapipe/yt8m_baseline_saved_model.tar.gz -C /tmp/mediapipe
+    ```
+
+3.  Build and run the inference binary.
+
+    ```bash
+    bazel build -c opt --define='MEDIAPIPE_DISABLE_GPU=1' \
+      mediapipe/examples/desktop/youtube8m:model_inference
+
+    # segment_size is the number of seconds window of frames.
+    # overlap is the number of seconds adjacent segments share.
+    GLOG_logtostderr=1 bazel-bin/mediapipe/examples/desktop/youtube8m/model_inference \
+      --calculator_graph_config_file=mediapipe/graphs/youtube8m/local_video_model_inference.pbtxt \
+      --input_side_packets=input_sequence_example_path=/tmp/mediapipe/output.tfrecord,input_video_path=/absolute/path/to/the/local/video/file,output_video_path=/tmp/mediapipe/annotated_video.mp4,segment_size=5,overlap=4
+    ```
+
+4.  View the annotated video.