Initial roadmap.

PiperOrigin-RevId: 247637897

Author: alanchiao

tensorflow_model_optimization/g3doc/_book.yaml

@@ -19,6 +19,8 @@ upper_tabs:
         path: /model_optimization/guide/get_started
       - title: Optimize further
         path: /model_optimization/guide/optimize_further
+      - title: Roadmap
+        path: /model_optimization/guide/roadmap
 
       - heading: Weight pruning
       - title: Overview

tensorflow_model_optimization/g3doc/guide/roadmap.md

@@ -0,0 +1,16 @@
+# TensorFlow model optimization roadmap
+
+**Updated: May 9th, 2019**
+
+## Quantization
+* Post training quantization for hybrid kernels -- [Launched](https://medium.com/tensorflow/introducing-the-model-optimization-toolkit-for-tensorflow-254aca1ba0a3)
+* Post training quantization for (8b) fixed-point kernels
+* Training with quantization for (8b) fixed-point kernels
+* Post training quantization for reduced-float (16b) kernels
+* Extend post and during training APIs to (8b) fixed-point RNNs
+* Training with quantization for low bit-width (< 8b) fixed-point kernels
+
+## Pruning / Sparsity
+* Magnitude based weight pruning during training - Launched
+* Support for sparse model execution
+