浏览代码

updating feedback

/docs
Wesley Mareovich Smith 5 年前
当前提交
0b94b497
共有 4 个文件被更改,包括 1021 次插入28 次删除
  1. 3
      README.md
  2. 37
      com.unity.perception/Documentation~/GettingStarted.md
  3. 8
      com.unity.perception/Documentation~/SetupSteps.md
  4. 1001
      com.unity.perception/Documentation~/images/banner2.PNG

3
README.md


<img src="com.unity.perception/Documentation~/images/unity-wide.png" align="middle" width="3000"/>
<img src="com.unity.perception/Documentation~/images/banner.PNG" align="middle"/>
<img src="com.unity.perception/Documentation~/images/banner2.PNG" align="middle"/>
# Perception
com.unity.perception provides a toolkit for generating large-scale datasets for perception-based machine learning training and validation. It is focused on a handful of camera-based use cases for now and will ultimately expand to other forms of sensors and machine learning tasks.

## Documenation
#### Click [here](Documentation~/SetupSteps.md) to setup a Perception project
#### Click [here](Documentation~/GettingStarted.md) to get the started with Perception
* [Overview](Documentation~/GroundTruth-Overview.md)

37
com.unity.perception/Documentation~/GettingStarted.md


# Getting Started with SynthDet
This will provide a step by step instructions on creating a new scene using the Perception features to create semantic data and image captures. These steps should work with both options for setup steps of using a existing project or creating a new project. The goal is to have a working scene by the end of these instructions that will provide you with a dataset, rgb images captures, and segmentic data.
If you have not already done the setup steps for the project, click [here](Documentation~/SetupSteps.md) to start project setup.
## Step 1: Create a new scene and camera
1. Create a new scene File-> New Scene
2. Save the Scene File-> Save and give it a name, i.e created scene name is PerceptionScene

2. Add a script called Perception Camera
5. Fill out the Description field in the script
1. i.e example description is Perception Sample
2. Add a **Perception Camera** component
2. Select the cube
1. Adjust the position transform of the cube to 1, 0, 5 (X,Y,Z)
2. Adjust the rotation of the cube to 0, 45, 0 (X,Y,Z)
3. In the Hierarchy window right click -> Go to 3D Object -> Select Cube
4. Change the name of the cube to Box in the Inspector panel
1. Adjust the position transform of the cube to -1, 0, 5 (X,Y,Z)
2. Adjust the rotation of the cube to 0, 45, 0 (X,Y,Z)
4. In the Hierarchy window right click -> Go to 3D Object -> Select Cube
5. Change the name of the cube to Crate in the Inspector panel
1. Adjust the position transform of the cube to 0, 0, 6.5 (X,Y,Z)
2. Adjust the rotation of the cube to 0, 45, 0 (X,Y,Z)
1. Create 3 Cubes
2. Change the names of the cubes to have 3 seperate names Cube, Box, Crate
3. Position the Cubes in front of the FOV of the main Camera, example image of the completed scene for reference down below
6. For each object in the scene that was created, from the inspector panel add the script called Labeling
2. For each object in the scene that was created, from the inspector panel add the script called **Labeling**
7. In the Project panel right click -> Perception -> Labeling Configuration
8. Select the Labeling Configuration created in the project panel
3. In the Project panel right click -> Perception -> Labeling Configuration
4. Select the **Labeling Configuration** created in the project panel
2. In the label text field add the same text that the Label script contains on the object
2. In the label text field add the same text that the Label script contains on the objects created in the scene (i.e Cube, Box, Crate)
3. Add a numerical value to the value field
1. Make sure the labels all have different values, for this example use values of 10,000
<img src="docs/images/LabelingConfigurationFinished.PNG" align="middle"/>

## Step 3: Checking local files
1. Press play in the editor and allow the scene to run for 10 seconds before ending playmode
2. In the console log you will see a Shutdown in Progress message that will show a file path to the location of the created data from the labeling objects
2. In the console log you will see a Shutdown in Progress message that will show a file path to the location of the generated dataset
1. RGB capture
2. Semantic Segmentation
1. RGB captures
2. Semantic segmentation images
4. Dataset
4. JSON Dataset
<img src="docs/images/rgb_2.png" align="middle"/>
<img src="docs/images/segmentation_2.png" align="middle"/>

8
com.unity.perception/Documentation~/SetupSteps.md


2. In the Package Manager window find and click the ***+*** button in the upper lefthand corner of the window
3. Select the ***add package from disk*** option
4. Navigate to the com.unity.perception folder in your cloned repository and select the package.json file
3. Navigate to the root of your project and open your project's `<project root>/Packages/manifest.json` in a text editor
1. To allow the compilation and running of tests, add `"testables": [ "com.unity.perception" ]`
2. For an example `manifest.json`, see `TestProjects/PerceptionTest/Packages/manifest.json`
3. For more on the `manifest.json` schema, see the [Package Manager documentation](https://docs.unity3d.com/Packages/com.unity.package-manager-ui@1.7/manual/index.html#advanced-package-topics)
4. Once you have a project with Perception SDK installed you can move forward to the Getting Started walkthrough
3. Once you have a project with Perception SDK installed you can move forward to the Getting Started walkthrough
Once completed you can move on to the getting started steps, click [here](Documentation~/GettingStarted.md) to start project setup.
## Suggested IDE Setup
For closest standards conformity and best experience overall, JetBrains Rider or Visual Studio w/ JetBrains Resharper are suggested. For optimal experience, perform the following additional steps:

1001
com.unity.perception/Documentation~/images/banner2.PNG
文件差异内容过多而无法显示
查看文件

正在加载...
取消
保存