SCDS/FtcRobotControllerSDK
7
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Updated Using a TensorFlow Pre trained Model to Detect Everyday Objects (markdown)

FTC Engineering
2020-10-29 18:56:49 -04:00
parent 768ebd179d
commit 4276170a4d
1 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
Using-a-TensorFlow-Pre-trained-Model-to-Detect-Everyday-Objects.md

@ -1,4 +1,7 @@
### Introduction ### Introduction
Teams have the option of using a custom TensorFlow Lite object detection model that was trained to detect objects other than the current season's game elements. This tutorial demonstrates how use a pretrained model to look for and track everyday objects. This particular tutorial uses the OnBot Java programming tool, but teams can also use Android Studio or the Blocks programming tool to implement this example op mode. Teams have the option of using a custom TensorFlow object detection model to detect objects other than the current season's game elements. This tutorial demonstrates how use a pretrained model to look for and track everyday objects. This particular tutorial uses the OnBot Java programming tool, but teams can also use Android Studio or the Blocks programming tool to implement this example.
This tutorial assumes that you have already completed the steps in [this TensorFlow tutorial](Using-a-Custom-TensorFlow-Model-with-Java). If you have not yet completed the steps in the [previous TensorFlow tutorial](Using-a-Custom-TensorFlow-Model-with-Java), then please do so before continuing with this tutorial. This tutorial assumes that you have already completed the steps in [a previous TensorFlow tutorial](Using-a-Custom-TensorFlow-Model-with-Java). If you have not yet completed the steps in the [previous TensorFlow tutorial](Using-a-Custom-TensorFlow-Model-with-Java), then please do so before continuing with this tutorial.
### Obtaining the Pretrained Model and Label Map
The custom inference model must be in the form of a TensorFlow Lite (.tflite) file. For this example, we will use the same Mobilenet object detection model that is used in Google's [example TensorFlow Object Detection Android app](https://github.com/tensorflow/examples/tree/master/lite/examples/object_detection/android).