Reference Task library in the model guides

PiperOrigin-RevId: 328242690
Change-Id: Icaaba6c49ed201090d8e2cfa42c7f666143e8927

tensorflow/lite/g3doc/convert/metadata.md

@@ -408,8 +408,22 @@ Flatbuffers library.
 
 ### Read the metadata in Java
 
-Note: the Java Metadata Extractor library is available as an Android library
-dependency: `org.tensorflow:tensorflow-lite-metadata`.
+To use the Metadata Extractor library in your Android app, we recommend using
+the
+[TensorFlow Lite Metadata AAR hosted at JCenter](https://bintray.com/google/tensorflow/tensorflow-lite-metadata).
+It contains the `MetadataExtractor` class, as well as the FlatBuffers Java
+bindings for the
+[metadata schema](https://github.com/tensorflow/tflite-support/blob/master/tensorflow_lite_support/metadata/metadata_schema.fbs)
+and the
+[model schema](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/schema/schema.fbs).
+
+You can specify this in your `build.gradle` dependencies as follows:
+
+```build
+dependencies {
+    implementation 'org.tensorflow:tensorflow-lite-metadata:0.0.0-nightly'
+}
+```
 
 You can initialize a `MetadataExtractor` object with a `ByteBuffer` that points
 to the model:

tensorflow/lite/g3doc/guide/android.md

@@ -16,7 +16,7 @@ to continuously classify whatever it sees from the device's rear-facing camera.
 The application can run either on device or emulator.
 
 Inference is performed using the TensorFlow Lite Java API and the
-[TensorFlow Lite Android Support Library](https://github.com/tensorflow/tflite-support/blob/master/tensorflow_lite_support/java/README.md).
+[TensorFlow Lite Android Support Library](../inference_with_metadata/lite_support.md).
 The demo app classifies frames in real-time, displaying the top most probable
 classifications. It allows the user to choose between a floating point or
 [quantized](https://www.tensorflow.org/lite/performance/post_training_quantization)
@@ -41,6 +41,36 @@ as a starting point.
 The following sections contain some useful information for working with
 TensorFlow Lite on Android.
 
+### Use the TensorFlow Lite Task Library
+
+TensorFlow Lite Task Library contains a set of powerful and easy-to-use
+task-specific libraries for app developers to create ML experiences with TFLite.
+It provides optimized out-of-box model interfaces for popular machine learning
+tasks, such as image classification, question and answer, etc. The model
+interfaces are specifically designed for each task to achieve the best
+performance and usability. Task Library works cross-platform and is supported on
+Java, C++, and Swift (coming soon).
+
+To use the Support Library in your Android app, we recommend using the AAR
+hosted at JCenter for
+[Task Vision library](https://bintray.com/google/tensorflow/tensorflow-lite-task-vision)
+and
+[Task Text library](https://bintray.com/google/tensorflow/tensorflow-lite-task-text)
+, respectively.
+
+You can specify this in your `build.gradle` dependencies as follows:
+
+```build
+dependencies {
+    implementation 'org.tensorflow:tensorflow-lite-task-vision:0.0.0-nightly'
+    implementation 'org.tensorflow:tensorflow-lite-task-text:0.0.0-nightly'
+}
+```
+
+See the introduction in the
+[TensorFlow Lite Task Library overview](../inference_with_metadata/task_library/overview.md)
+for more details.
+
 ### Use the TensorFlow Lite Android Support Library
 
 The TensorFlow Lite Android Support Library makes it easier to integrate models
@@ -52,8 +82,19 @@ It supports common data formats for inputs and outputs, including images and
 arrays. It also provides pre- and post-processing units that perform tasks such
 as image resizing and cropping.
 
+To use the Support Library in your Android app, we recommend using the
+[TensorFlow Lite Support Library AAR hosted at JCenter](https://bintray.com/google/tensorflow/tensorflow-lite-support).
+
+You can specify this in your `build.gradle` dependencies as follows:
+
+```build
+dependencies {
+    implementation 'org.tensorflow:tensorflow-lite-support:0.0.0-nightly'
+}
+```
+
 To get started, follow the instructions in the
-[TensorFlow Lite Android Support Library README.md](https://github.com/tensorflow/tflite-support/blob/master/tensorflow_lite_support/java/README.md).
+[TensorFlow Lite Android Support Library](../inference_with_metadata/lite_support.md).
 
 ### Use the TensorFlow Lite AAR from JCenter
 

tensorflow/lite/g3doc/guide/hosted_models.md

@@ -4,8 +4,8 @@ The following is an incomplete list of pre-trained models optimized to work with
 TensorFlow Lite.
 
 To get started choosing a model, visit <a href="../models">Models</a> page with
-end-to-end examples, or pick a [TensorFlow Lite model from TensorFlow Hub]
-(https://tfhub.dev/s?deployment-format=lite).
+end-to-end examples, or pick a
+[TensorFlow Lite model from TensorFlow Hub](https://tfhub.dev/s?deployment-format=lite).
 
 Note: The best model for a given application depends on your requirements. For
 example, some applications might benefit from higher accuracy, while others
@@ -16,6 +16,9 @@ models to find the optimal balance between size, performance, and accuracy.
 
 For more information about image classification, see
 <a href="../models/image_classification/overview.md">Image classification</a>.
+Explore the TensorFlow Lite Task Library for instructions about
+[how to integrate image classification models](../inference_with_metadata/task_library/image_classifier)
+in just a few lines of code.
 
 ### Quantized models
 
@@ -24,7 +27,8 @@ classification models offer the smallest model size and fastest performance, at
 the expense of accuracy. The performance values are measured on Pixel 3 on
 Android 10.
 
-You can find many [quantized models](https://tfhub.dev/s?deployment-format=lite&module-type=image-classification&q=quantized)
+You can find many
+[quantized models](https://tfhub.dev/s?deployment-format=lite&module-type=image-classification&q=quantized)
 from TensorFlow Hub and get more model information there.
 
 Model name                  | Paper and model                                                                                                                                                                   | Model size | Top-1 accuracy | Top-5 accuracy | CPU, 4 threads | NNAPI
@@ -54,8 +58,8 @@ Inception_V4_quant          | [paper](https://arxiv.org/abs/1602.07261), [tflite
 Note: The model files include both TF Lite FlatBuffer and Tensorflow frozen
 Graph.
 
-Note: Performance numbers were benchmarked on Pixel-3 (Android 10).
-Accuracy numbers were computed using the
+Note: Performance numbers were benchmarked on Pixel-3 (Android 10). Accuracy
+numbers were computed using the
 [TFLite image classification evaluation tool](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/tools/evaluation/tasks/imagenet_image_classification).
 
 ### Floating point models
@@ -65,7 +69,8 @@ performance. <a href="../performance/gpu">GPU acceleration</a> requires the use
 of floating point models. The performance values are measured on Pixel 3 on
 Android 10.
 
-You can find many [image classification models](https://tfhub.dev/s?deployment-format=lite&module-type=image-classification)
+You can find many
+[image classification models](https://tfhub.dev/s?deployment-format=lite&module-type=image-classification)
 from TensorFlow Hub and get more model information there.
 
 Model name            | Paper and model                                                                                                                                                                           | Model size | Top-1 accuracy | Top-5 accuracy | CPU, 4 threads | GPU    | NNAPI
@@ -102,8 +107,9 @@ The following image classification models were created using
 <a href="https://cloud.google.com/automl/">Cloud AutoML</a>. The performance
 values are measured on Pixel 3 on Android 10.
 
-You can find these models in [TensorFlow Hub](https://tfhub.dev/s?deployment-format=lite&q=MnasNet)
-and get more model information there.
+You can find these models in
+[TensorFlow Hub](https://tfhub.dev/s?deployment-format=lite&q=MnasNet) and get
+more model information there.
 
 Model Name       | Paper and model                                                                                                                                                | Model size | Top-1 accuracy | Top-5 accuracy | CPU, 4 threads | GPU     | NNAPI
 ---------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------: | ---------: | -------------: | -------------: | -------------: | ------: | ----:
@@ -116,16 +122,20 @@ MnasNet_1.0_192  | [paper](https://arxiv.org/abs/1807.11626), [tflite&pb](https:
 MnasNet_1.0_224  | [paper](https://arxiv.org/abs/1807.11626), [tflite&pb](https://storage.cloud.google.com/download.tensorflow.org/models/tflite/mnasnet_1.0_224_09_07_2018.tgz)  | 17 Mb      | 74.08%         | 91.75%         | 19.4 ms        | 8.7 ms  | 19 ms
 MnasNet_1.3_224  | [paper](https://arxiv.org/abs/1807.11626), [tflite&pb](https://storage.cloud.google.com/download.tensorflow.org/models/tflite/mnasnet_1.3_224_09_07_2018.tgz)  | 24 Mb      | 75.24%         | 92.55%         | 27.9 ms        | 10.6 ms | 22.0 ms
 
-Note: Performance numbers were benchmarked on Pixel-3 (Android 10).
-Accuracy numbers were computed using the
+Note: Performance numbers were benchmarked on Pixel-3 (Android 10). Accuracy
+numbers were computed using the
 [TFLite image classification evaluation tool](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/tools/evaluation/tasks/imagenet_image_classification).
 
 ## Object detection
 
 For more information about object detection, see
-<a href="../models/object_detection/overview.md">Object detection</a>.
+<a href="../models/object_detection/overview.md">Object detection</a>. Explore
+the TensorFlow Lite Task Library for instructions about
+[how to integrate object detection models](../inference_with_metadata/task_library/object_detector)
+in just a few lines of code.
 
-Please find [object detection models](https://tfhub.dev/s?deployment-format=lite&module-type=image-object-detection)
+Please find
+[object detection models](https://tfhub.dev/s?deployment-format=lite&module-type=image-object-detection)
 from TensorFlow Hub.
 
 ## Pose estimation
@@ -133,21 +143,29 @@ from TensorFlow Hub.
 For more information about pose estimation, see
 <a href="../models/pose_estimation/overview.md">Pose estimation</a>.
 
-Please find [pose estimation models](https://tfhub.dev/s?deployment-format=lite&module-type=image-pose-detection)
+Please find
+[pose estimation models](https://tfhub.dev/s?deployment-format=lite&module-type=image-pose-detection)
 from TensorFlow Hub.
 
 ## Image segmentation
 
 For more information about image segmentation, see
-<a href="../models/segmentation/overview.md">Segmentation</a>.
+<a href="../models/segmentation/overview.md">Segmentation</a>. Explore the
+TensorFlow Lite Task Library for instructions about
+[how to integrate image segmentation models](../inference_with_metadata/task_library/image_segmenter)
+in just a few lines of code.
 
-Please find [image segmentation models](https://tfhub.dev/s?deployment-format=lite&module-type=image-segmentation)
+Please find
+[image segmentation models](https://tfhub.dev/s?deployment-format=lite&module-type=image-segmentation)
 from TensorFlow Hub.
 
 ## Question and Answer
 
-For more information about text classification with Mobile BERT, see
-<a href="../models/bert_qa/overview.md">Question And Answer</a>.
+For more information about question and answer with MobileBERT, see
+<a href="../models/bert_qa/overview.md">Question And Answer</a>. Explore the
+TensorFlow Lite Task Library for instructions about
+[how to integrate question and answer models](../inference_with_metadata/task_library/bert_question_answerer)
+in just a few lines of code.
 
 Please find [Mobile BERT model](https://tfhub.dev/tensorflow/mobilebert/1) from
 TensorFlow Hub.

tensorflow/lite/g3doc/inference_with_metadata/lite_support.md

@@ -40,6 +40,10 @@ dependencies {
 }
 ```
 
+Explore the
+[TensorFlow Lite Support Library AAR hosted at JCenter](https://bintray.com/google/tensorflow/tensorflow-lite-support)
+for different versions of the Support Library.
+
 ### Basic image manipulation and conversion
 
 The TensorFlow Lite Support Library has a suite of basic image manipulation

tensorflow/lite/g3doc/inference_with_metadata/task_library/bert_nl_classifier.md

-# Bert natural language classifier
+# Integrate BERT natural language classifier
 
 The Task Library `BertNLClassifier` API is very similar to the `NLClassifier`
 that classifies input text into different categories, except that this API is

tensorflow/lite/g3doc/inference_with_metadata/task_library/bert_question_answerer.md

-# Bert question answerer
+# Integrate BERT question answerer
 
 The Task Library `BertQuestionAnswerer` API loads a Bert model and answers
 questions based on the content of a given passage. For more information, see the
@@ -21,10 +21,7 @@ The following models are compatible with the `BertNLClassifier` API.
     [TensorFlow Lite Model Maker for Question Answer](https://www.tensorflow.org/lite/tutorials/model_maker_question_answer).
 
 *   The
-    [pretrained ALBERT models on TensorFlow Hub](https://tfhub.dev/tensorflow/albert_lite_base/1).
-
-*   The
-    [pretrained MobileBERT models on TensorFlow Hub](https://tfhub.dev/tensorflow/tfjs-model/mobilebert/1).
+    [pretrained BERT models on TensorFlow Hub](https://tfhub.dev/tensorflow/collections/lite/task-library/bert-question-answerer/1).
 
 *   Custom models that meet the
     [model compatibility requirements](#model-compatibility-requirements).

tensorflow/lite/g3doc/inference_with_metadata/task_library/image_classifier.md

@@ -40,7 +40,7 @@ API.
     [pretrained image classification models from TensorFlow Lite Hosted Models](https://www.tensorflow.org/lite/guide/hosted_models#image_classification).
 
 *   The
-    [pretrained image classification models on TensorFlow Hub](https://tfhub.dev/s?deployment-format=lite&module-type=image-classification).
+    [pretrained image classification models on TensorFlow Hub](https://tfhub.dev/tensorflow/collections/lite/task-library/image-classifier/1).
 
 *   Models created by
     [AutoML Vision Edge Image Classification](https://cloud.google.com/vision/automl/docs/edge-quickstart).

tensorflow/lite/g3doc/inference_with_metadata/task_library/image_segmenter.md

@@ -29,7 +29,7 @@ The following models are guaranteed to be compatible with the `ImageSegmenter`
 API.
 
 *   The
-    [pretrained image segmentation models on TensorFlow Hub](https://tfhub.dev/s?deployment-format=lite&module-type=image-segmentation).
+    [pretrained image segmentation models on TensorFlow Hub](https://tfhub.dev/tensorflow/collections/lite/task-library/image-segmenter/1).
 
 *   Custom models that meet the
     [model compatibility requirements](#model-compatibility-requirements).

tensorflow/lite/g3doc/inference_with_metadata/task_library/nl_classifier.md

-# Natural language classifier
+# Integrate Natural language classifier
 
 The Task Library's `NLClassifier` API classifies input text into different
 categories, and is a versatile and configurable API that can handle most text

tensorflow/lite/g3doc/inference_with_metadata/task_library/object_detector.md

@@ -32,7 +32,7 @@ The following models are guaranteed to be compatible with the `ObjectDetector`
 API.
 
 *   The
-    [pretrained object detection models on TensorFlow Hub](https://tfhub.dev/s?deployment-format=lite&module-type=image-object-detection&publisher=google,tensorflow).
+    [pretrained object detection models on TensorFlow Hub](https://tfhub.dev/tensorflow/collections/lite/task-library/object-detector/1).
 
 *   Models created by
     [AutoML Vision Edge Object Detection](https://cloud.google.com/vision/automl/object-detection/docs).

tensorflow/lite/g3doc/inference_with_metadata/task_library/overview.md

@@ -6,7 +6,7 @@ It provides optimized out-of-box model interfaces for popular machine learning
 tasks, such as image classification, question and answer, etc. The model
 interfaces are specifically designed for each task to achieve the best
 performance and usability. Task Library works cross-platform and is supported on
-Java, C++, and Swift(coming soon).
+Java, C++, and Swift (coming soon).
 
 ## What to expect from the Task Library