UPdate tflite converter diagram.

Rename URL paths.

PiperOrigin-RevId: 216889190

tensorflow/contrib/lite/g3doc/_book.yaml

@@ -38,15 +38,16 @@ upper_tabs:
         path: /lite/ios
       - title: TensorFlow Lite for Raspberry Pi
         path: /lite/rpi
-      - heading: TFLite Converter
+
+      - heading: TF Lite converter
       - title: Overview
-        path: /lite/tflite_convert/
-      - title: Python API
-        path: /lite/tflite_convert/python_api
-      - title: Command Line Examples
-        path: /lite/tflite_convert/cmdline_examples
-      - title: Command Line Reference
-        path: /lite/tflite_convert/cmdline_reference
+        path: /lite/convert/
+      - title: Python API guide
+        path: /lite/convert/python_api
+      - title: Command line examples
+        path: /lite/convert/cmdline_examples
+      - title: Command line reference
+        path: /lite/convert/cmdline_reference
 
       - title: TF Mobile
         style: accordion

tensorflow/contrib/lite/g3doc/_index.yaml

@@ -132,7 +132,7 @@ landing_page:
         TensorFlow Lite Converter.
       buttons:
       - label: Read the converter guide
-        path: /lite/tflite_convert/python_api
+        path: /lite/convert/
         classname: button button-primary tfo-button-primary
     - heading: Deploy
       icon:

tensorflow/contrib/lite/g3doc/tflite_convert/cmdline_examples.md → tensorflow/contrib/lite/g3doc/convert/cmdline_examples.md

@@ -1,4 +1,4 @@
-# TensorFlow Lite Converter command-line examples
+# Converter command-line examples
 
 This page shows how to use the TensorFlow Lite Converter in the command line.
 
@@ -306,12 +306,12 @@ Sample output files can be seen here below. Note that it is the same
 <table><tr>
   <td>
     <a target="_blank" href="https://storage.googleapis.com/download.tensorflow.org/example_images/toco_AT_IMPORT.dot.pdf">
-      <img src="https://www.tensorflow.org/images/tflite_convert/tflite_convert_before.png"/>
+      <img src="../images/convert/sample_before.png"/>
     </a>
   </td>
   <td>
     <a target="_blank" href="https://storage.googleapis.com/download.tensorflow.org/example_images/toco_AFTER_TRANSFORMATIONS.dot.pdf">
-      <img src="https://www.tensorflow.org/images/tflite_convert/tflite_convert_after.png"/>
+      <img src="../images/convert/sample_after.png"/>
     </a>
   </td>
 </tr>

tensorflow/contrib/lite/g3doc/tflite_convert/cmdline_reference.md → tensorflow/contrib/lite/g3doc/convert/cmdline_reference.md

@@ -1,4 +1,4 @@
-# TensorFlow Lite Converter command-line glossary
+# Converter command-line reference
 
 This page is complete reference of command-line flags used by the TensorFlow
 Lite Converter's command line starting from TensorFlow 1.9 up until the most

tensorflow/contrib/lite/g3doc/convert/index.md

@@ -0,0 +1,19 @@
+# TensorFlow Lite Converter
+
+The TensorFlow Lite Converter takes a TensorFlow graph file and creates a graph
+file used by the TensorFlow Lite interpreter.
+
+## From model training to device deployment
+
+After a TensorFlow model is trained, the TensorFlow Lite converter uses that
+model to generate a TensorFlow Lite [FlatBuffer](https://google.github.io/flatbuffers/)
+file (`.tflite`). The converter supports as input:
+[SavedModels](https://www.tensorflow.org/guide/saved_model#using_savedmodel_with_estimators),
+frozen graphs (models generated by
+[freeze_graph.py](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/tools/freeze_graph.py)),
+and `tf.keras` models.  The TensorFlow Lite `FlatBuffer` file is deployed to a
+client device (generally a mobile or embedded device), and the TensorFlow Lite
+interpreter uses the compressed model for on-device inference. This conversion
+process is shown in the diagram below:
+
+![TFLite converter workflow](../images/convert/workflow.svg)

tensorflow/contrib/lite/g3doc/tflite_convert/python_api.md → tensorflow/contrib/lite/g3doc/convert/python_api.md

@@ -1,4 +1,4 @@
-# TensorFlow Lite Converter & Interpreter Python API reference
+# Converter Python API guide
 
 This page provides examples on how to use the TensorFlow Lite Converter and the
 TensorFlow Lite interpreter using the Python API.