Clarify and highlight API compatibility with pruning.

PiperOrigin-RevId: 284038715

Author: alanchiao

README.md

@@ -25,10 +25,10 @@ pip install --user --upgrade tensorflow-model-optimization
 For release details, see our
 [release notes](https://github.com/tensorflow/model-optimization/releases).
 
-TensorFlow Model Optimization requires either Tensorflow 1.x for versions 1.14+
-or the nightly build of [TensorFlow](https://www.tensorflow.org/install) (pip
-package `tf-nightly`). Note that for the nightly build, you need to use
-tf.compat.v1 since 2.x is the default now.
+For the required version of TensorFlow and other compatibility information, see
+the API Compatibility Matrix section of the Overview page for the technique you
+intend to use. For instance, for pruning, the Overview page is
+[here](https://www.tensorflow.org/model_optimization/guide/pruning).
 
 Since TensorFlow is *not* included as a dependency of the TensorFlow Model
 Optimization package (in `setup.py`), you must explicitly install the TensorFlow

tensorflow_model_optimization/g3doc/guide/pruning/index.md

@@ -22,14 +22,17 @@ The technique is being evaluated in various speech applications, such as
 speech recognition and text-to-speech, and has been experimented on across
 various vision and translation models.
 
-Users can apply this technique using APIs for Keras on Tensorflow 1.x for
-versions 1.14+ and tf-nightly in both graph and eager execution. Note that in
-tf-nightly, you must use tf.compat.v1 since 2.x is the default now.
+### API Compatibility Matrix
+Users can apply pruning with the following APIs:
 
-Note: The pruning API is only compatible with `tf.distribute` when using graph
-execution.
+* Model building: `tf.keras` with only Sequential and Functional models
+* TensorFlow versions: TF 1.x for versions 1.14+
+* TensorFlow execution mode: both graph and eager
+* Distributed training: `tf.distribute` with only graph execution
 
-It is on our roadmap to bring full support to TF 2.x and eager execution.
+It is on our roadmap to add support in the following areas:
+* TF 2.x (moderate testing has been done)
+* [Minimal Subclassed model support](https://github.com/tensorflow/model-optimization/issues/155)
 
 ## Results