boards/beaglebone/ai-64/edge_ai_apps/inference_models.rst

@@ -69,17 +69,17 @@ Each DNN must have the following 3 components:
 
 #. **model**: This directory contains the DNN being targeted to infer
 #. **artifacts**: This directory contains the artifacts generated after the
-   compilation of DNN for SDK, and described in :ref:`pub_edgeai_compile_artifacts`
+   compilation of DNN for SDK, and described in :ref:`ai_64_edgeai_compile_artifacts`
 #. **param.yaml**: A configuration file in yaml format to provide basic
    information about DNN, and associated pre and post processing parameters.
-   More details can be find :ref:`pub_edgeai_params`
+   More details can be find :ref:`ai_64_edgeai_params`
 
 .. _ai_64_edgeai_params:
 
 Param file format
 -----------------
 
-Each DNN has it’s own pre-process, inference and post-process
+Each DNN has its own pre-process, inference and post-process
 parameters to get the correct output. This information is typically available in
 the training software that was used to train the model. In order to convey this
 information to the SDK in a standardized fashion, we have defined a set of

boards/beaglebone/ai-64/edge_ai_apps/performance_visualizer.rst

@@ -6,7 +6,7 @@ Performance Visualization Tool
 The performance visualization tool can be used to view all the performance
 statistics recorded when running the edge AI C++ demo application. This includes
 the CPU and HWA loading, DDR bandwidth, Junction Temperatures and FPS obtained.
-Refer to :ref:`pub_edgeai_available_statistics` for details on the performance 
+Refer to :ref:`ai_64_edgeai_available_statistics` for details on the performance 
 metrics available to be plotted.
 
 This tool works as follows:
@@ -20,7 +20,7 @@ This tool works as follows:
       which can be easily viewed by a visiting a URL in any browser. This script uses
       Streamlit package to update the graphs in real-time, as the Edge AI application
       runs in parallel. However, since Streamlit is not supported in the SDK out of box,
-      this script needs to run on docker. Please refer to :ref:`pub_edgeai_docker_env`
+      this script needs to run on docker. Please refer to :ref:`ai_64_edgeai_docker_env`
       for building and running a docker container.
 
 
@@ -100,4 +100,4 @@ the above image:
 
 For the first three metrics, there is a choice to view line graphs with a 30s
 history or bar graphs with only the real-time values. The remaining eleven have
-real-time bar graphs as the only option.
+real-time bar graphs as the only option.
\ No newline at end of file

boards/beaglebone/ai-64/edge_ai_apps/running_advance_demos.rst

@@ -9,7 +9,7 @@ file.
 
 From a repo of input sources, output sources and models one can define advance
 dataflows which connect them in various configurations. Details on configuration
-file parameters can be found in :ref:`pub_edgeai_configuration`
+file parameters can be found in :ref:`ai_64_edgeai_configuration`
 
 Single input multi inference demo
 ---------------------------------

boards/beaglebone/ai-64/edge_ai_apps/running_simple_demos.rst

@@ -20,7 +20,7 @@ Running Python based demo applications
 Python based demos are simple executable scripts written for image
 classification, object detection and semantic segmentation. Demos are
 configured using a YAML file. Details on configuration file parameters can
-be found in :ref:`pub_edgeai_configuration`
+be found in :ref:`ai_64_edgeai_configuration`
 
 Sample configuration files for out of the box demos can be found in
 ``edge_ai_apps/configs`` this folder also contains a template config file

boards/beaglebone/ai-64/edge_ai_apps/sdk_components.rst

@@ -7,7 +7,7 @@ The BeagleBone® AI-64 Linux for Edge AI can be divided into 3 parts, Applicatio
 BeagleBone® AI-64 Linux and Processor SDK RTOS. Users can get the latest application
 updates and bug fixes from the public repositories (GitHub and git.ti.com)
 which aligns with the SDK releases done quarterly. One can also build every component
-from source by following the steps here, :ref:`pub_edgeai_sdk_development_flow`
+from source by following the steps in the `TI Edge AI SDK development flow <https://software-dl.ti.com/jacinto7/esd/edgeai-sdk-j721e/latest/exports/docs/development_flow.html>`__.
 
 .. figure:: ./images/edgeai-sdk-components.png
    :scale: 50
@@ -52,7 +52,7 @@ for various computer vision tasks. A few example models are packaged as part of
 the SDK to run out-of-box demos. More can be downloaded using a download script
 made available in the edge_ai_apps repo.
 
-For more details on the the pre-imported models and related documentation please visit:
+For more details on the pre-imported models and related documentation please visit:
 https://github.com/TexasInstruments/edgeai-modelzoo
 
 
@@ -74,7 +74,7 @@ edgeai-gst-plugins
 This repo provides the source of custom GStreamer plugins which helps offload
 tasks to TDA4 hardware accelerators and advanced DSPs with the help of
 edgeai-tiovx-modules. The repo gets downloaded, built and installed as part
-of the :ref:`pub_edgeai_install_dependencies` step.
+of the :ref:`ai_64_edgeai_install_dependencies` step.
 
 Source code and documentation: https://github.com/TexasInstruments/edgeai-gst-plugins
 
@@ -85,7 +85,7 @@ edgeai-tiovx-modules
 This repo provides OpenVx modules which help access underlying hardware
 accelerators in the  TDA4 SoC and serves as a bridge between GStreamer
 custom elements and underlying OpenVx custom kernels. The repo gets downloaded,
-built and installed as part of the :ref:`pub_edgeai_install_dependencies` step.
+built and installed as part of the :ref:`ai_64_edgeai_install_dependencies` step.
 
 Source code and documentation: https://github.com/TexasInstruments/edgeai-tiovx-modules
 
@@ -103,7 +103,7 @@ For more information visit `Processor SDK RTOS Getting Started Guide <https://so
 .. _ai_64_edgeai_psdk_linux:
 
 BeagleBone® AI-64 Linux
-===================
+========================
 
 The BeagleBone® AI-64 Linux for Edge AI  gets all the Linux kernel, filesystem, device-drivers and more
 from BeagleBone® AI-64 Linux

boards/beaglebone/ai-64/edge_ai_apps/test_report.rst

@@ -228,4 +228,4 @@ Multi Input Multi Output
 
 .. note::
     * Video file from RTSP server used for RTSP input test
-    * Please refer to the :ref:`pub_edgeai_known_issues` section for more details
+    * Please refer to the `TI Edge AI SDK release notes and known issues <https://software-dl.ti.com/jacinto7/esd/edgeai-sdk-j721e/latest/exports/docs/release_notes.html>`__ for more details