Detailed instructions covering all the important steps from installing Unity Editor, to creating your first Perception project, building a randomized Scene, and generating large-scale synthetic datasets by leveraging the power of Unity Simulation. No prior Unity experience required.
## Documentation
In-depth documentation on inidividual components of the package.
## Documentation
|Feature|Description|
|---|---|
|[Labeling](com.unity.perception/Documentation~/GroundTruthLabeling.md)|A component that marks a GameObject and its descendants with a set of labels|
|[LabelConfig](com.unity.perception/Documentation~/GroundTruthLabeling.md#label-config)|An asset that defines a taxonomy of labels for ground truth generation|
|[Perception Camera](com.unity.perception/Documentation~/PerceptionCamera.md)|Captures RGB images and ground truth from a [Camera](https://docs.unity3d.com/Manual/class-Camera.html).|
|[DatasetCapture](com.unity.perception/Documentation~/DatasetCapture.md)|Ensures sensors are triggered at proper rates and accepts data for the JSON dataset.|
|[Randomization (Experimental)](com.unity.perception/Documentation~/Randomization/Index.md)|The Randomization tool set lets you integrate domain randomization principles into your simulation.|
[SynthDet](https://github.com/Unity-Technologies/SynthDet) is an end-to-end solution for training a 2D object detection model using synthetic data.
[Perception Tutorial](com.unity.perception/Documentation~/Tutorial/TUTORIAL.md): Detailed instructions covering all the important steps from installing Unity Editor, to creating your first Perception project, building a randomized Scene, and generating large-scale synthetic datasets by leveraging the power of Unity Simulation.
[Perception Manual](com.unity.perception/Documentation~/index.md): Sample projects and documentation of the SDK.
The [Unity Simulation Smart Camera Example](https://github.com/Unity-Technologies/Unity-Simulation-Smart-Camera-Outdoor) illustrates how Perception could be used in a smart city or autonomous vehicle simulation. You can generate datasets locally or at scale in [Unity Simulation](https://unity.com/products/unity-simulation).
## Local development
The repository includes two projects for local development in `TestProjects` folder, one set up for HDRP and the other for URP.
* To allow navigating to code in all packages included in your project, in your Unity Editor, navigate to `Edit -> Preferences... -> External Tools` and check `Generate all .csproj files.`
## Known issues
* The Linux Editor 2019.4.7f1 and 2019.4.8f1 might hang when importing HDRP-based Perception projects. For Linux Editor support, use 2019.4.6f1 or 2020.1
Unique seeds per Sampler have been replaced with one global random seed configured via the ScenarioConstants of a Scenario
Replaced ScenarioBase.GenerateRandomSeed() with ScenarioBase.NextRandomState()
Samplers now derive their random state from the static SamplerState class instead of individual scenarios to allow parameters and samplers to be used outside of the context of a scenario
Replaced ScenarioBase.GenerateRandomSeed() with SamplerState.NextRandomState() and SamplerState.CreateGenerator()
In this phase of the Perception tutorial, you will start from downloading and installing Unity Editor and the Perception package. You will then use our sample assets and provided components to easily generate a synthetic dataset for training an object-detection model.
Through-out the tutorial, lines starting with bullet points followed by **"Action:"** denote the individual actions you will need to perform in order to progress through the tutorial. This is while non-bulleted lines will provide additional context and explanation around the actions. If in a hurry, you can just follow the actions!
Through-out the tutorial, lines starting with bullet points followed by **":green_circle: Action:"** denote the individual actions you will need to perform in order to progress through the tutorial. This is while non-bulleted lines will provide additional context and explanation around the actions. If in a hurry, you can just follow the actions!
Steps included this phase of the tutorial:
- [Step 1: Download Unity Editor and Create a New Project](#step-1)
- [Step 8: Verify Data Using Dataset Insights](#step-8)
### <aname="step-1">Step 1: Download Unity Editor and Create a New Project</a>
* **Action**: Navigate to [this](https://unity3d.com/get-unity/download/archive) page to download and install the latest version of **Unity Editor 2019.4.x**. (The tutorial has not yet been fully tested on newer versions.)
* **:green_circle: Action**: Navigate to [this](https://unity3d.com/get-unity/download/archive) page to download and install the latest version of **Unity Editor 2019.4.x**. (The tutorial has not yet been fully tested on newer versions.)
* **Action**: Make sure the _**Linux Build Support (Mono)**_ and _**Visual Studio**_ installation options are checked when selecting modules during installation.
* **:green_circle: Action**: Make sure the _**Linux Build Support (Mono)**_ and _**Visual Studio**_ installation options are checked when selecting modules during installation.
* **Action**: Open Unity and create a new project using the Universal Render Pipeline. Name your new project _**Perception Tutorial**_, and specify a desired location as shown below.
* **:green_circle: Action**: Open Unity and create a new project using the Universal Render Pipeline. Name your new project _**Perception Tutorial**_, and specify a desired location as shown below.
Once your new project is created and loaded, you will be presented with the Unity Editor interface. From this point on, whenever we refer to _**the editor**_, we mean Unity Editor.
* **Action**: From the top menu bar, open _**Window**_ -> _**Package Manager**_.
* **:green_circle: Action**: From the top menu bar, open _**Window**_ -> _**Package Manager**_.
* **Action**: Click on the _**+**_ sign at the top-left corner of the _**Package Manager**_ window and then choose the option _**Add package from git URL...**_.
* **Action**: Enter the address `com.unity.perception` and click _**Add**_.
* **:green_circle: Action**: Click on the _**+**_ sign at the top-left corner of the _**Package Manager**_ window and then choose the option _**Add package from git URL...**_.
* **:green_circle: Action**: Enter the address `com.unity.perception` and click _**Add**_.
**Note:** If you would like a specific version of the package, you can append the version to the end of the url. For example `com.unity.perception@0.1.0-preview.5`. For this tutorial, **we do not need to add a version**. You can also install the package from a local clone of the Perception repository. More information on installing local packages is available [here](https://docs.unity3d.com/Manual/upm-ui-local.html).
> :information_source: If you would like to install a specific version of the package, you can append the version to the end of the url. For example `com.unity.perception@0.1.0-preview.5`. For this tutorial, **we do not need to add a version**. You can also install the package from a local clone of the Perception repository. More information on installing local packages is available [here](https://docs.unity3d.com/Manual/upm-ui-local.html).
It will take some time for the manager to download and import the package. Once the operation finishes, you will see the newly download Perception package automatically selected in the _**Package Manager**_, as depicted below:
Each package can come with a set of samples. As seen in the righthand panel, the Perception package includes a sample named _**Tutorial Files**_, which will be required for completing this tutorial. The sample files consist of example foreground and background objects, randomizers, shaders, and other useful elements to work with during this tutorial. **Foreground** objects are those that the eventual machine learning model will try to detect, and **background** objects will be placed in the background as distractors for the model.
* **Action**: In the _**Package Manager**_ window, from the list of _**Samples**_ for the Perception package, click on the _**Import into Project**_ button for the sample named _**Tutorial Files**_.
* **:green_circle: Action**: In the _**Package Manager**_ window, from the list of _**Samples**_ for the Perception package, click on the _**Import into Project**_ button for the sample named _**Tutorial Files**_.
Once the sample files are imported, they will be placed inside the `Assets/Samples/Perception` folder in your Unity project. You can view your project's folder structure and access your files from the _**Project**_ tab of the editor, as seen in the image below:
* **Action**: **(For URP projects only)** The _**Project**_ tab contains a search bar; use it to find the file named `ForwardRenderer.asset`, as shown below:
* **:green_circle: Action**: **(For URP projects only)** The _**Project**_ tab contains a search bar; use it to find the file named `ForwardRenderer.asset`, as shown below:
* **Action**: **(For URP projects only)** Click on the found file to select it. Then, from the _**Inspector**_ tab of the editor, click on the _**Add Renderer Feature**_ button, and select _**Ground Truth Renderer Feature**_ from the dropdown menu:
* **:green_circle: Action**: **(For URP projects only)** Click on the found file to select it. Then, from the _**Inspector**_ tab of the editor, click on the _**Add Renderer Feature**_ button, and select _**Ground Truth Renderer Feature**_ from the dropdown menu:
### <aname="step-3">Step 3: Setup a Scene for Your Perception Simulation</a>
Simply put, in Unity, Scenes contain any object that exists in the world. This world can be a game, or in this case, a perception-oriented simulation. Every new project contains a Scene named `SampleScene`, which is automatically opened when the project is created. This Scene comes with several objects and settings that we do not need, so let's create a new one.
* **Action**: In the _**Project**_ tab, right-click on the `Assets/Scenes` folder and click _**Create -> Scene**_. Name this new Scene `TutorialScene` and **double-click on it to open it**.
* **:green_circle: Action**: In the _**Project**_ tab, right-click on the `Assets/Scenes` folder and click _**Create -> Scene**_. Name this new Scene `TutorialScene` and **double-click on it to open it**.
The _**Hierarchy**_ tab of the editor displays all the Scenes currently loaded, and all the objects currently present in each loaded Scene, as shown below:
<palign="center">
As seen above, the new Scene already contains a camera (`Main Camera`) and a light (`Directional Light`). We will now modify the camera's field of view and position to prepare it for the tutorial.
* **Action**: Click on `Main Camera` and in the _**Inspector**_ tab, modify the camera's `Position`, `Rotation`, `Projection` and `Size` to match the screenshot below. (Note that `Size` only becomes available once you set `Projection` to `Orthographic`)
* **:green_circle: Action**: Click on `Main Camera` and in the _**Inspector**_ tab, modify the camera's `Position`, `Rotation`, `Projection` and `Size` to match the screenshot below. (Note that `Size` only becomes available once you set `Projection` to `Orthographic`)
<palign="center">
<imgsrc="Images/camera_prep.png"/>
For this tutorial, we prefer our light to not cast any shadows, therefore:
* **Action**: Click on `Directional Light` and in the _**Inspector**_ tab, set `Shadow Type` to `No Shadows`.
* **:green_circle: Action**: Click on `Directional Light` and in the _**Inspector**_ tab, set `Shadow Type` to `No Shadows`.
* **Action**: Select `Main Camera` again and in the _**Inspector**_ tab, click on the _**Add Component**_ button.
* **Action**: Start typing `Perception Camera` in the search bar that appears, until the `Perception Camera` script is found, with a **#** icon to the left:
* **:green_circle: Action**: Select `Main Camera` again and in the _**Inspector**_ tab, click on the _**Add Component**_ button.
* **:green_circle: Action**: Start typing `Perception Camera` in the search bar that appears, until the `Perception Camera` script is found, with a **#** icon to the left:
* **Action**: Click on this script to add it as a component. Your camera is now a `Perception` camera.
* **:green_circle: Action**: Click on this script to add it as a component. Your camera is now a `Perception` camera.
**Note:** You may now see a warning regarding asynchronous shader compilation in the UI for the `Perception Camera` component. To fix this issue, from the top menu bar go to _**Edit -> Project Settings… -> Editor**_ and under _**Shader Compilation**_ settings, disable _**Asynchronous Shader Compilation**_.
> :information_source: You may now see a warning regarding asynchronous shader compilation in the UI for the `Perception Camera` component. To fix this issue, from the top menu bar go to _**Edit -> Project Settings… -> Editor**_ and under _**Shader Compilation**_ settings, disable _**Asynchronous Shader Compilation**_.
Adding components is the standard way in which objects can have various kinds of logic and data attached to them in Unity. This includes objects placed within the Scene (called GameObjects), such as the camera above, or objects outside of a Scene, in your project folders (called Prefabs).
To speed-up your perception workflow, the Perception package comes with five common labelers for object-detection tasks; however, if you are comfortable with code, you can also add your own custom labelers. The labelers that come with the Perception package cover **3D bounding boxes, 2D bounding boxes, object counts, object information (pixel counts and ids), and semantic segmentation images (each object rendered in a unique colour)**. We will use four of these in this tutorial.
* **Action**: Click on the _**+**_ button at the bottom right corner of the empty labeler list and select `BoundingBox2DLabeler`.
* **Action**: Repeat the above step to add `ObjectCountLabeler`, `RenderedObjectInfoLabeler`, `SemanticSegmentationLabeler`.
* **:green_circle: Action**: Click on the _**+**_ button at the bottom right corner of the empty labeler list and select `BoundingBox2DLabeler`.
* **:green_circle: Action**: Repeat the above step to add `ObjectCountLabeler`, `RenderedObjectInfoLabeler`, `SemanticSegmentationLabeler`.
Once you add the labelers, the _**Inspector**_ view of the `Perception Camera` component will look like this:
You will notice each added labeler has a `Label Config` field. By adding a label configuration here you can instruct the labeler to look for certain labels within the scene and ignore the rest. To do that, we should first create label configurations.
* **Action**: In the _**Project**_ tab, right-click the `Assets` folder, then click _**Create -> Perception -> Id Label Config**_.
* **:green_circle: Action**: In the _**Project**_ tab, right-click the `Assets` folder, then click _**Create -> Perception -> Id Label Config**_.
* **Action**: Rename the newly created `IdLabelConfig` asset to `TutorialIdLabelConfig`.
* **:green_circle: Action**: Rename the newly created `IdLabelConfig` asset to `TutorialIdLabelConfig`.
Click on this asset to bring up its _**Inspector**_ view. In there, you can specify the labels that this config will keep track of. You can type in labels, add any labels defined in the project (through being added to prefabs), and import/export this label config as a JSON file. A new label config like this one contains an empty list of labels.
* **Action**: In the _**Project**_ tab, right-click the `Assets` folder, then click _**Create -> Perception -> Semantic Segmentation Label Config**_. Name this asset `TutorialSemanticSegmentationLabelConfig`.
* **:green_circle: Action**: In the _**Project**_ tab, right-click the `Assets` folder, then click _**Create -> Perception -> Semantic Segmentation Label Config**_. Name this asset `TutorialSemanticSegmentationLabelConfig`.
* **Action**: Select the `Main Camera` object from the Scene _**Hierarchy**_, and in the _**Inspector**_ tab, assign the newly created `TutorialIdLabelConfig` to the first three labelers. To do so, you can either drag and drop the former into the corresponding fields for each labeler, or click on the small circular button in front of the `Id Label Config` field, which brings up an asset selection window filtered to only show compatible assets. Assign `TutorialSemanticSegmentationLabelConfig` to the fourth labeler. The `Perception Camera` component will now look like the image below:
* **:green_circle: Action**: Select the `Main Camera` object from the Scene _**Hierarchy**_, and in the _**Inspector**_ tab, assign the newly created `TutorialIdLabelConfig` to the first three labelers. To do so, you can either drag and drop the former into the corresponding fields for each labeler, or click on the small circular button in front of the `Id Label Config` field, which brings up an asset selection window filtered to only show compatible assets. Assign `TutorialSemanticSegmentationLabelConfig` to the fourth labeler. The `Perception Camera` component will now look like the image below:
In Unity, Prefabs are essentially reusable GameObjects that are stored to disk, along with all their child GameObjects, components, and property values. Let's see what our sample prefabs include.
* **Action**: In the _**Project**_ tab, navigate to `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Foreground Objects/Phase 1/Prefabs`
* **Action**: Double click the file named `drink_whippingcream_lucerne.prefab` to open the Prefab asset.
* **:green_circle: Action**: In the _**Project**_ tab, navigate to `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Foreground Objects/Phase 1/Prefabs`
* **:green_circle: Action**: Double click the file named `drink_whippingcream_lucerne.prefab` to open the Prefab asset.
When you open the Prefab asset, you will see the object shown in the Scene tab and its components shown on the right side of the editor, in the _**Inspector**_ tab:
Note that each object can have multiple labels assigned, and thus appear as different objects to labelers with different label configurations. For instance, you may want your semantic segmentation labeler to detect all cream cartons as `dairy_product`, while your bounding box labeler still distinguishes between different types of dairy product. To achieve this, you can add a `dairy_product` label to all your dairy products, and then in your label configuration for semantic segmentation, only add the `dairy_product` label, and not any specific products or brand names.
For this tutorial, we have already added the `Labeling` component to all the foreground Prefabs; however, if you are making your own Prefabs, you can easily add a `Labeling` component to them using the _**Add Component**_ button in the screenshot above.
For this tutorial, we have already prepared the foreground Prefabs for you and added the `Labeling` component to all of them. These Prefabs were based on 3D scans of the actual grocery items. If you are making your own Prefabs, you can easily add a `Labeling` component to them using the _**Add Component**_ button visible in the bottom right corner of the screenshot above.
**Note:** If you would like to start from `.fbx` models, the Perception package lets you quickly create Prefabs from multiple models. Just select all your models and from the top menu bar select _**Assets -> Perception -> Create Prefabs from Selected Models**_. The newly created Prefabs will be placed in the same folders as their corresponding models.
> :information_source: If you are interested in knowing more about the process of creating Unity compatible 3D models for use in Perception, you can visit [this page](https://github.com/Unity-Technologies/SynthDet/blob/master/docs/CreatingAssets.md). Once you have 3D models in `.fbx` format, the Perception package lets you quickly create Prefabs from multiple models. Just select all your models and from the top menu bar select _**Assets -> Perception -> Create Prefabs from Selected Models**_. The newly created Prefabs will be placed in the same folders as their corresponding models.
* **Action**: Select **all the files** inside the `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Foreground Objects/Phase 1/Prefabs` folder.
* **Action**: From the _**Inspector**_ tab, enable `Use Automatic Labeling for All Selected Items`, and then select `Use asset name` as the labeling scheme.
* **:green_circle: Action**: Select **all the files** inside the `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Foreground Objects/Phase 1/Prefabs` folder.
* **:green_circle: Action**: From the _**Inspector**_ tab, enable `Use Automatic Labeling for All Selected Items`, and then select `Use asset name` as the labeling scheme.
<palign="center">
<imgsrc="Images/autolabel.png"width="400"/>
* **Action**: Click _**Add Automatic Labels of All Selected Assets to Config...**_.
* **:green_circle: Action**: Click _**Add Automatic Labels of All Selected Assets to Config...**_.
* **Action**: Add the list of labels to `TutorialIdLabelConfig` and `TutorialSemanticSegmentationLabelConfig` by clicking the _**Add All Labels**_ button for both.
* **:green_circle: Action**: Add the list of labels to `TutorialIdLabelConfig` and `TutorialSemanticSegmentationLabelConfig` by clicking the _**Add All Labels**_ button for both.
<palign="center">
<imgsrc="Images/labelconfigs.png"width="800"/>
</p>
**Note:** Since we used automatic labels here and added them to our configurations, we are confident that the labels in the configurations match the labels of our objects. In cases where you decide to add manual labels to objects and configurations, make sure you use the exact same labels, otherwise, the objects for which a matching label is not found in your configurations will not be detected by the labelers that are using those configurations.
> :information_source: Since we used automatic labels here and added them to our configurations, we are confident that the labels in the configurations match the labels of our objects. In cases where you decide to add manual labels to objects and configurations, make sure you use the exact same labels, otherwise, the objects for which a matching label is not found in your configurations will not be detected by the labelers that are using those configurations.
* **Action**: In the _**Project**_ tab, navigate to `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Foreground Objects/Phase 1/Prefabs`.
* **Action**: Drag and drop any of the Prefabs inside this folder into the Scene.
* **Action**: Click on the **▷** (play) button located at the top middle section of the editor to run your simulation.
* **:green_circle: Action**: In the _**Project**_ tab, navigate to `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Foreground Objects/Phase 1/Prefabs`.
* **:green_circle: Action**: Drag and drop any of the Prefabs inside this folder into the Scene.
* **:green_circle: Action**: Click on the **▷** (play) button located at the top middle section of the editor to run your simulation.
Since we have visualizations enabled on our `Perception Camera`, you should now see a bounding box being drawn around the object you put in the scene, and the object itself being colored according to its label's color in `TutorialSemanticSegmentationLabelConfig`, similar to the image below:
In this tutorial, you will learn how to use the provided Randomizers, as well as how to create new ones that are custom-fitted to your randomization needs.
* **Action**: Create a new GameObject in your Scene by right-clicking in the _**Hierarchy**_ tab and clicking `Create Empty`.
* **Action**: Rename your new GameObject to `Simulation Scenario`.
* **Action**: In the _**Inspector**_ view of this new object, add a new `Fixed Length Scenario` component.
* **:green_circle: Action**: Create a new GameObject in your Scene by right-clicking in the _**Hierarchy**_ tab and clicking `Create Empty`.
* **:green_circle: Action**: Rename your new GameObject to `Simulation Scenario`.
* **:green_circle: Action**: In the _**Inspector**_ view of this new object, add a new `Fixed Length Scenario` component.
Each `Scenario` executes a number of `Iteration`s, and each Iteration carries on for a number of frames. These are timing elements you can leverage in order to customize your Scenarios and the timing of your randomizations. You will learn how to use Iterations and frames in Phase 2 of this tutorial. For now, we will use the `Fixed Length Scenario`, which is a special kind of Scenario that runs for a fixed number of frames during each Iteration, and is sufficient for many common use-cases. Note that at any given time, you can have only one Scenario active in your Scene.
There are a number of settings and properties you can modify here. `Quit On Complete` instructs the simulation to quit once this Scenario has completed executing. We can see here that the Scenario has been set to run for 100 Iterations, and that each Iteration will run for one frame. But this is currently an empty `Scenario`, so let's add some Randomizers.
* **Action**: Click _**Add Randomizer**_, and from the list choose `BackgroundObjectPlacementRandomizer`.
* **:green_circle: Action**: Click _**Add Randomizer**_, and from the list choose `BackgroundObjectPlacementRandomizer`.
* **Action**: Click _**Add Folder**_, and from the file explorer window that opens, choose the folder `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Background Objects/Prefabs`.
* **:green_circle: Action**: Click _**Add Folder**_, and from the file explorer window that opens, choose the folder `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Background Objects/Prefabs`.
* **Action**: Set the rest of the properties according to the image below. That is, `Depth = 0, Layer Count = 2, Separation Distance = 0.5, Placement Area = (6,6)`.
* **:green_circle: Action**: Set the rest of the properties according to the image below. That is, `Depth = 0, Layer Count = 2, Separation Distance = 0.5, Placement Area = (6,6)`.
* **Action**: Click on the **▷** (play) button located at the top middle section of the editor to run your simulation.
* **:green_circle: Action**: Click on the **▷** (play) button located at the top middle section of the editor to run your simulation.
<palign="center">
<imgsrc="Images/play.png"width ="500"/>
As seen in the image above, what we have now is just a beige-colored wall of shapes. This is because so far, we are only spawning them, and the beige color of our light is what gives them their current look. To make this background more useful, let's add a couple more `Randomizers`.
**Note:** If at this point you don't see any objects being displayed, make sure the Separation Distance for `BackgroundObjectPlacementRandomizer` is (6,6) and not (0,0).
> :information_source: If at this point you don't see any objects being displayed, make sure the Separation Distance for `BackgroundObjectPlacementRandomizer` is (6,6) and not (0,0).
**Note:** If your _**Game**_ tab has a different field of view than the one shown here, change the aspect ratio of your _**Game**_ tab to `4:3`, as shown below:
> :information_source: If your _**Game**_ tab has a different field of view than the one shown here, change the aspect ratio of your _**Game**_ tab to `4:3`, as shown below:
* **Action**: Repeat the previous steps to add `TextureRandomizer`, `HueOffsetRandomizer`, and `RotationRandomizer`.
* **:green_circle: Action**: Repeat the previous steps to add `TextureRandomizer`, `HueOffsetRandomizer`, and `RotationRandomizer`.
* **Action**: In the UI snippet for `TextureRandomizer`, click _**Add Folder**_ and choose `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Background Textures`.
* **:green_circle: Action**: In the UI snippet for `TextureRandomizer`, click _**Add Folder**_ and choose `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Background Textures`.
* **Action**: In the UI snippet for `RotationRandomizer`, verify that all the minimum values for the three ranges are `0` and that maximum values are `360`.
* **:green_circle: Action**: In the UI snippet for `RotationRandomizer`, verify that all the minimum values for the three ranges are `0` and that maximum values are `360`.
Your list of Randomizers should now look like the screenshot below:
To make sure each Randomizer knows which objects it should work with, we will use an object tagging and querying workflow that the bundled Randomizers already use. Each Randomizer can query the Scene for objects that carry certain types of `RandomizerTag` components. For instance, the `TextureRandomizer` queries the Scene for objects that have a `TextureRandomizerTag` component (you can change this in code!). Therefore, in order to make sure our background Prefabs are affected by the `TextureRandomizer` we need to make sure they have `TextureRandomizerTag` attached to them.
* **Action**: In the _**Project**_ tab, navigate to `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Background Objects/Prefabs`.
* **Action**: Select all the files inside and from the _**Inspector**_ tab add a `TextureRandomizerTag` to them. This will add the component to all the selected files.
* **Action**: Repeat the above step to add `HueOffsetRandomizerTag` and `RotationRandomizerTag` to all selected Prefabs.
* **:green_circle: Action**: In the _**Project**_ tab, navigate to `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Background Objects/Prefabs`.
* **:green_circle: Action**: Select all the files inside and from the _**Inspector**_ tab add a `TextureRandomizerTag` to them. This will add the component to all the selected files.
* **:green_circle: Action**: Repeat the above step to add `HueOffsetRandomizerTag` and `RotationRandomizerTag` to all selected Prefabs.
Once the above step is done, the _**Inspector**_ tab for a background Prefab should look like this:
It is now time to spawn and randomize our foreground objects.
* **Action**: Add `ForegroundObjectPlacementRandomizer` to your list of Randomizers. Click _**Add Folder**_ and select `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Foreground Objects/Phase 1/Prefabs`.
* **Action**: Set these values for the above Randomizer: `Depth = -3, Separation Distance = 1.5, Placement Area = (5,5)`.
* **:green_circle: Action**: Add `ForegroundObjectPlacementRandomizer` to your list of Randomizers. Click _**Add Folder**_ and select `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Foreground Objects/Phase 1/Prefabs`.
* **:green_circle: Action**: Set these values for the above Randomizer: `Depth = -3, Separation Distance = 1.5, Placement Area = (5,5)`.
* **Action**: From the _**Project**_ tab select all the foreground Prefabs located in `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Foreground Objects/Phase 1/Prefabs`, and add a `RotationRandomizerTag` component to them.
* **:green_circle: Action**: From the _**Project**_ tab select all the foreground Prefabs located in `Assets/Samples/Perception/0.6.0-preview.1/Tutorial Files/Foreground Objects/Phase 1/Prefabs`, and add a `RotationRandomizerTag` component to them.
* **Action**: Drag `ForegroundObjectPlacementRandomizer` using the striped handle bar (on its left side) and drop it above `RotationRandomizer`.
* **:green_circle: Action**: Drag `ForegroundObjectPlacementRandomizer` using the striped handle bar (on its left side) and drop it above `RotationRandomizer`.
Your full list of Randomizers should now look like the screenshot below:
You are now ready to generate your first dataset. Our current setup will produce 100 frames of annotated captures.
* **Action** Click **▷** (play) again and this time let the simulation finish. This should take only a few seconds.
* **:green_circle: Action** Click **▷** (play) again and this time let the simulation finish. This should take only a few seconds.
While the simulation is running, your _**Game**_ view will quickly generate frames similar to the gif below (note: visualization for `SemanticSegmentationLabeler` is disabled here):
<imgsrc="Images/dataset_written.png"/>
</p>
* **Action**: Navigate to the dataset path addressed in the _**Console**_.
* **:green_circle: Action**: Navigate to the dataset path addressed in the _**Console**_.
In this folder, you will find a few types of data, depending on your `Perception Camera` settings. These can include:
- Logs
The output dataset includes a variety of information about different aspects of the active sensors in the Scene (currently only one), as well as the ground-truth generated by all active labelers. [This page](https://github.com/Unity-Technologies/com.unity.perception/blob/master/com.unity.perception/Documentation%7E/Schema/Synthetic_Dataset_Schema.md) provides a comprehensive explanation on the schema of this dataset. We strongly recommend having a look at the page once you have completed this tutorial.
* **Action**: To get a quick feel of how the data is stored, open the folder whose name starts with `Dataset`, then open the file named `captures_000.json`. This file contains the output from `BoundingBox2DLabeler`. The `captures` array contains the position and rotation of the sensor (camera), the position and rotation of the ego (sensor group, currently only one), and the annotations made by `BoundingBox2DLabeler` for all visible objects defined in its label configuration. For each visible object, the annotations include:
* **:green_circle: Action**: To get a quick feel of how the data is stored, open the folder whose name starts with `Dataset`, then open the file named `captures_000.json`. This file contains the output from `BoundingBox2DLabeler`. The `captures` array contains the position and rotation of the sensor (camera), the position and rotation of the ego (sensor group, currently only one), and the annotations made by `BoundingBox2DLabeler` for all visible objects defined in its label configuration. For each visible object, the annotations include:
* `label_id`: The numerical id assigned to this object's label in the labeler's label configuration
* `label_name`: The object's label, e.g. `candy_minipralines_lindt`
* `instance_id`: Unique instance id of the object
* **Action**: Review the JSON meta-data and the images captured for the first annotated frame, and verify that the objects within them match.
* **:green_circle: Action**: Review the JSON meta-data and the images captured for the first annotated frame, and verify that the objects within them match.
### <aname="step-8">Step 8: Verify Data Using Dataset Insights</a>
* **Action**: Download and install [Docker Desktop](https://www.docker.com/products/docker-desktop)
* **Action**: Open a command line interface (Command Prompt on Windows, Terminal on Mac OS, etc.) and type the following command to run the Dataset Insights Docker image:
* **:green_circle: Action**: Download and install [Docker Desktop](https://www.docker.com/products/docker-desktop)
* **:green_circle: Action**: Open a command line interface (Command Prompt on Windows, Terminal on Mac OS, etc.) and type the following command to run the Dataset Insights Docker image:
* **Action**: The image is now running on your computer. Open a web browser and navigate to `http://localhost:8888` to open the Jupyter notebook:
* **:green_circle: Action**: The image is now running on your computer. Open a web browser and navigate to `http://localhost:8888` to open the Jupyter notebook:
* **Action**: To make sure your data is properly mounted, navigate to the `data` folder. If you see the dataset's folders there, we are good to go.
* **Action**: Navigate to the `datasetinsights/notebooks` folder and open `Perception_Statistics.ipynb`.
* **Action**: Once in the notebook, remove the `/<GUID>` part of the `data_root = /data/<GUID>` path. Since the dataset root is already mapped to `/data`, you can use this path directly.
* **:green_circle: Action**: To make sure your data is properly mounted, navigate to the `data` folder. If you see the dataset's folders there, we are good to go.
* **:green_circle: Action**: Navigate to the `datasetinsights/notebooks` folder and open `Perception_Statistics.ipynb`.
* **:green_circle: Action**: Once in the notebook, remove the `/<GUID>` part of the `data_root = /data/<GUID>` path. Since the dataset root is already mapped to `/data`, you can use this path directly.
<palign="center">
<imgsrc="Images/jupyter2.png"/>
</p>
* **Action**: Follow the instructions laid out in the notebook and run each code block to view its outputs.
* **:green_circle: Action**: Follow the instructions laid out in the notebook and run each code block to view its outputs.
This concludes Phase 1 of the Perception tutorial. In the next phase, you will dive a little bit into randomization code and learn how to build your own custom Randomizer. [Click here to continue to Phase 2: Custom Randomizations](Phase2.md)
This concludes Phase 1 of the Perception tutorial. In the next phase, you will dive a little bit into randomization code and learn how to build your own custom Randomizer.
**[Continue to Phase 2: Custom Randomizations](Phase2.md)**
We need to create two C# classes for our light randomization, `MyLightRandomizer` and `MyLightRandomizerTag`. The first of these will sample random values and assign them to the intensity and color of the light, and the second class will be the component that will be added to `Directional Light`, making it a target of `MyLightRandomizer`.
* **Action**: In the _**Project**_ tab, right-click on the `Scripts` folder and select _**Create -> C# Script**_. Name your new script file `MyLightRandomizer.cs`.
* **Action**: Create another script and name it `MyLightRandomizerTag.cs`.
* **Action**: Double-click `MyLightRandomizer.cs` to open it in _**Visual Studio**_.
* **:green_circle: Action**: In the _**Project**_ tab, right-click on the `Scripts` folder and select _**Create -> C# Script**_. Name your new script file `MyLightRandomizer.cs`.
* **:green_circle: Action**: Create another script and name it `MyLightRandomizerTag.cs`.
* **:green_circle: Action**: Double-click `MyLightRandomizer.cs` to open it in _**Visual Studio**_.
* **Action**: Remove the contents of the class and copy/paste the code below:
* **:green_circle: Action**: Remove the contents of the class and copy/paste the code below:
```
```C#
using System;
using UnityEngine;
using UnityEngine.Experimental.Perception.Randomization.Parameters;
The purpose of this piece of code is to obtain a random float parameter and assign it to the light's `Intensity` field on the start of every Iteration. Let's go through the code above and understand each part. The `FloatParameter` field makes it possible for us to define a randomized float parameter and modify its properties from the editor UI, similar to how we already modified the properties for the previous Randomizers we used.
**Note:** If you look at the _**Console**_ tab of the editor now, you will see an error regarding `MyLightRandomizerTag` not being found. This is to be expected, since we have not yet created this class; the error will go away once we create the class later.
> :information_source: If you look at the _**Console**_ tab of the editor now, you will see an error regarding `MyLightRandomizerTag` not being found. This is to be expected, since we have not yet created this class; the error will go away once we create the class later.
* **Action**: Add `MyLightRandomizer` to the list of Randomizers in `SimulationScenario`.
* **:green_circle: Action**: Add `MyLightRandomizer` to the list of Randomizers in `SimulationScenario`.
You will notice that the Randomizer's UI snippet contains one Parameter named `Light Intensity Parameter`. This is the same Parameter we added in the code block above. Here, you can set the sampling distribution (`Value`) and `Range` for this float Parameter:
* **Action**: In the UI snippet for `MyLightRandomzier`, set the minimum and maximum for range to 0.5 and 3.
* **:green_circle: Action**: In the UI snippet for `MyLightRandomzier`, set the minimum and maximum for range to 0.5 and 3.
This range of intensities is arbitrary but will give us a typically nice lighting without excessive darkness or burnt-out highlights.
* **Action**: Open `MyLightRandomizerTag.cs` and replace its contents with the code below:
* **:green_circle: Action**: Open `MyLightRandomizerTag.cs` and replace its contents with the code below:
```
```C#
using UnityEngine;
using UnityEngine.Experimental.Perception.Randomization.Randomizers;
Notice there is a `RequireComponent(typeof(Light))` line at the top. This line makes it so that you can only add the `MyLightRandomizerTag` component to an object that already has a `Light` component attached. This way, the Randomizers that query for this tag can be confident that the found objects have a `Light` component and can thus be Randomized.
* **Action**: Select `Directional Light` in the Scene's _**Hierarchy**_, and in the _**Inspector**_ tab, add a `My Light Randomizer Tag` component.
* **Action**: Run the simulation again and inspect how `Directional Light` now switches between different intensities. You can pause the simulation and then use the step button (to the right of the pause button) to move the simulation one frame forward and clearly see the varying light intensity
* **:green_circle: Action**: Select `Directional Light` in the Scene's _**Hierarchy**_, and in the _**Inspector**_ tab, add a `My Light Randomizer Tag` component.
* **:green_circle: Action**: Run the simulation again and inspect how `Directional Light` now switches between different intensities. You can pause the simulation and then use the step button (to the right of the pause button) to move the simulation one frame forward and clearly see the varying light intensity
* **Action**: Back inside `MyLightRandomizer.cs`, define a new `ColorRgbParameter`:
* **:green_circle: Action**: Back inside `MyLightRandomizer.cs`, define a new `ColorRgbParameter`:
* **Action**: Inside the code block that intensity was previously applied, add code for sampling color from the above Parameter and applying it:
* **:green_circle: Action**: Inside the code block that intensity was previously applied, add code for sampling color from the above Parameter and applying it:
```
```C#
foreach (var taggedObject in taggedObjects)
{
var light = taggedObject.GetComponent<Light>();
If you now check the UI snippet for `MyLightRandomizer`, you will notice that `Color Parameter` is added. This Parameter includes four separate randomized values for `Red`, `Green`, `Blue` and `Alpha`. Note that the meaningful range for all of these values is 0-1 (and not 0-255). You can see that the sampling range for red, green, and blue is currently also set to 0-1, which means the parameter covers a full range of colors. A color with (0,0,0) RGB components essentially emits no light. So, let's increase the minimum a bit to avoid such a scenario.
* **Action**: Increase the minimum value for red, green, and blue components to 0.4 (this is an arbitrary number that typically produces good-looking results).
* **:green_circle: Action**: Increase the minimum value for red, green, and blue components to 0.4 (this is an arbitrary number that typically produces good-looking results).
The UI for `My Light Randomizer` should now look like this:
* **Action**: Run the simulation for a few frames to observe the lighting color changing on each iteration.
* **:green_circle: Action**: Run the simulation for a few frames to observe the lighting color changing on each iteration.
### <aname="step-2">Step 2: Bundle Data and Logic Inside RandomizerTags</a>
Let's try this approach with our `Directional Light` object. We will create a duplicate of this light and then have the two lights use different ranges of intensity while both using the exact same float Parameter from `MyLightRandomizer.cs`.
* **Action**: Right-click on `Directional Light` in the Scene _**Hierarchy**_ and select _**Duplicate**_. The new light will automatically be named `Directional Light (1)`.
* **Action**: Change the Y rotation of `Directional Light (1)` to 60, as shown below:
* **:green_circle: Action**: Right-click on `Directional Light` in the Scene _**Hierarchy**_ and select _**Duplicate**_. The new light will automatically be named `Directional Light (1)`.
* **:green_circle: Action**: Change the Y rotation of `Directional Light (1)` to 60, as shown below:
* **Action**: Change the Y rotation of `Directional Light` to -60.
* **:green_circle: Action**: Change the Y rotation of `Directional Light` to -60.
* **Action**: Open `MyLightRandomizerTag.cs` and modify it to match the code below:
```
* **:green_circle: Action**: Open `MyLightRandomizerTag.cs` and modify it to match the code below:
```C#
using UnityEngine;
using UnityEngine.Experimental.Perception.Randomization.Randomizers;
This component is already added to both our lights. We now need to set our desired minimum and maximum intensities, and this can be done through the _**Inspector**_ view.
* **Action**: Select `Directional Light` and from the **Inspector** UI for the `MyLightRandomizerTag` component, set `Min Intensity` to 0.5 and `Max Intensity` to 3.
* **Action**: Repeat the above step for `Directional Light (1)` and set `Min Intensity` to 0 and `Max Intensity` to 0.4.
* **:green_circle: Action**: Select `Directional Light` and from the **Inspector** UI for the `MyLightRandomizerTag` component, set `Min Intensity` to 0.5 and `Max Intensity` to 3.
* **:green_circle: Action**: Repeat the above step for `Directional Light (1)` and set `Min Intensity` to 0 and `Max Intensity` to 0.4.
* **Action**: Select `SimulationScenario` and from the UI snippet for `My Light Randomizer`, change the range for `Light Intensity Parameter` from (0.5,3.5) to (0,1).
* **:green_circle: Action**: Select `SimulationScenario` and from the UI snippet for `My Light Randomizer`, change the range for `Light Intensity Parameter` from (0.5,3.5) to (0,1).
* **Action**: Open `MyLightRandomizer.cs` and modify it as seen below:
* **:green_circle: Action**: Open `MyLightRandomizer.cs` and modify it as seen below:
```
```C#
using System;
using UnityEngine;
using UnityEngine.Experimental.Perception.Randomization.Parameters;
Notice how we now fetch the `MyLightRandomizerTag` component from the tagged object and use its `SetIntensity` function instead of directly setting the intensity of the `Light` component.
* **Action**: Run your simulation, then pause it. Go to the _**Scene**_ view and inspect the color and intensity of each of the lights. Try turning each on and off to see how they affect the current frame.
* **:green_circle: Action**: Run your simulation, then pause it. Go to the _**Scene**_ view and inspect the color and intensity of each of the lights. Try turning each on and off to see how they affect the current frame.
[Click here to continue to Phase 3: Cloud](Phase3.md)
In order to use Unity Simulation, you need to first create a Unity account or login with your existing one. Once logged in, you will also need to sign-up for Unity Simulation.
* **Action** Click on the _**Cloud**_ button at the top-right corner of Unity Editor to open the _**Services**_ tab.
* **:green_circle: Action** Click on the _**Cloud**_ button at the top-right corner of Unity Editor to open the _**Services**_ tab.
<palign="center">
<imgsrc="Images/cloud_icon.png"width="400"/>
<imgsrc="Images/signin.png"width="400"/>
</p>
* **Action**: Click _**Sign in...**_ and follow the steps in the window that opens to sign in or create an account.
* **Action**: Sign up for a free trial of Unity Simulation [here](https://unity.com/products/unity-simulation).
* **:green_circle: Action**: Click _**Sign in...**_ and follow the steps in the window that opens to sign in or create an account.
* **:green_circle: Action**: Sign up for a free trial of Unity Simulation [here](https://unity.com/products/unity-simulation).
Unity Simulation is a cloud-based service that makes it possible for you to run hundreds of instances of Unity builds in order to generate massive amounts of data. The Unity Simulation service is billed on a per-usage basis, and the free trial offers up to $100 of free credit per month. In order to access the free trial, you will need to provide credit card information. **This information will be used to charge your account if you exceed the $100 monthly credit.** A list of hourly and daily rates for various computational resources is available in the page where you first register for Unity Simulation.
* **Action**: Return to Unity Editor. In the _**Services**_ tab click _**Select Organization**_ and choose the only available option (which typically has the same name as your Unity username).
* **:green_circle: Action**: Return to Unity Editor. In the _**Services**_ tab click _**Select Organization**_ and choose the only available option (which typically has the same name as your Unity username).
If you have used Unity before, you might have set-up multiple organizations for your account. In that case, choose whichever you would like to associate with this project.
* **Action**: Click _**Create**_ to create a new cloud project and connect your local project to it.
* **:green_circle: Action**: Click _**Create**_ to create a new cloud project and connect your local project to it.
### <aname="step-2">Step 2: Run Project on Unity Simulation</a>
* **Action**: From the _**Inspector**_ view of `Perception Camera`, disable real-time visualizations.
* **:green_circle: Action**: From the _**Inspector**_ view of `Perception Camera`, disable real-time visualizations.
* **Action**: From the top menu bar, open _**Edit -> Project Settings**_.
* **Action**: In the window that opens, navigate to the _**Player**_ tab, find the _**Scripting Backend**_ setting (under _**Other Settings**_), and change it to _**Mono**_:
* **:green_circle: Action**: From the top menu bar, open _**Edit -> Project Settings**_.
* **:green_circle: Action**: In the window that opens, navigate to the _**Player**_ tab, find the _**Scripting Backend**_ setting (under _**Other Settings**_), and change it to _**Mono**_:
* **Action**: Change _**Fullscreen Mode**_ to _**Windowed**_ and set a width and height of 800 by 600.
* **:green_circle: Action**: Change _**Fullscreen Mode**_ to _**Windowed**_ and set a width and height of 800 by 600.
* **Action**: Close _**Project Settings**_.
* **Action**: From the top menu bar, open _**Window -> Run in Unity Simulation**_.
* **:green_circle: Action**: Close _**Project Settings**_.
* **:green_circle: Action**: From the top menu bar, open _**Window -> Run in Unity Simulation**_.
* **Action**: Choose `TutorialScene` (which is the Scene we have been working in) as your _**Main Scene**_ and the `SimulationScenario` object as your _**Scenario**_.
* **:green_circle: Action**: Choose `TutorialScene` (which is the Scene we have been working in) as your _**Main Scene**_ and the `SimulationScenario` object as your _**Scenario**_.
* **Action**: Name your run `FirstRun`, set the number of iterations to `1000`, and instances to `20`.
* **Action**: Click _**Build and Run**_.
* **:green_circle: Action**: Name your run `FirstRun`, set the number of iterations to `1000`, and instances to `20`.
* **:green_circle: Action**: Click _**Build and Run**_.
* **Action**: Once the operation is complete, you can find the **Build ID**, **Run Definition ID**, and **Execution ID** of this Unity Simulation run in the _**Console**_ tab:
* **:green_circle: Action**: Once the operation is complete, you can find the **Build ID**, **Run Definition ID**, and **Execution ID** of this Unity Simulation run in the _**Console**_ tab:
<palign="center">
<imgsrc="Images/build_uploaded.png"/>
To keep track of the progress of your Unity Simulation run, you will need to use Unity Simulation's command-line interface (CLI). Detailed instructions for this CLI are provided [here](https://github.com/Unity-Technologies/Unity-Simulation-Docs/blob/master/doc/quickstart.md#download-unity-simulation-quickstart-materials). For the purposes of this tutorial, we will only go through the most essential commands, which will help us know when our Unity Simulation run is complete and where to find the produced dataset.
* **Action**: Download the latest version of `unity_simulation_bundle.zip` from [here](https://github.com/Unity-Technologies/Unity-Simulation-Docs/releases).
* **:green_circle: Action**: Download the latest version of `unity_simulation_bundle.zip` from [here](https://github.com/Unity-Technologies/Unity-Simulation-Docs/releases).
**Note**: If you are using a MacOS computer, we recommend using the _**curl**_ command from the Terminal to download the file, in order to avoid issues caused by the MacOS Gatekeeper when using the CLI. You can use these commands:
> :information_source: If you are using a MacOS computer, we recommend using the _**curl**_ command from the Terminal to download the file, in order to avoid issues caused by the MacOS Gatekeeper when using the CLI. You can use these commands:
* **Action**: Extract the zip archive you downloaded.
* **Action**: Open a command-line interface (Terminal on MacOS, cmd on Windows, etc.) and navigate to the extracted folder.
* **:green_circle: Action**: Extract the zip archive you downloaded.
* **:green_circle: Action**: Open a command-line interface (Terminal on MacOS, cmd on Windows, etc.) and navigate to the extracted folder.
If you downloaded the zip archive in the default location in your downloads folder, you can use these commands to navigate to it from the command-line:
You will now be using the _**usim**_ executable to interact with Unity Simulation through commands.
* **Action** To see a list of available commands, simply run `usim` once:
* **:green_circle: Action** To see a list of available commands, simply run `usim` once:
MacOS:
`USimCLI/mac/usim`
The first step is to login.
* **Action**: Login to Unity Simulation using the `usim login auth` command.
* **:green_circle: Action**: Login to Unity Simulation using the `usim login auth` command.
MacOS:
`USimCLI/mac/usim login auth`
`Press [ENTER] to open your browser to ...`
* **Action**: Press Enter to open a browser window for logging in.
* **:green_circle: Action**: Press Enter to open a browser window for logging in.
Once you have logged you will see this page:
**Note**: On MacOS, you might get errors related to permissions. In these cases, try running your commands with the `sudo` qualifier. For example:
`sudo USimCLI/mac/usim login auth`. This will ask for your MacOS account's password and should help overcome the permission issues.
> :warning: On MacOS, you might get errors related to permissions. If that is the case, modify the permissions on the `~/.usim` folder and its contents to give your user full read and write permission.
**Note : From this point on we will only include MacOS formatted commands in the tutorial, but all the `usim` commands we use will work in all supported operating systems.**
> :information_source: From this point on we will only include MacOS formatted commands in the tutorial, but all the `usim` commands we use will work in all supported operating systems.**
* **Action**: Return to your command-line interface. Get a list of cloud projects associated with your Unity account using the `usim get projects` command:
* **:green_circle: Action**: Return to your command-line interface. Get a list of cloud projects associated with your Unity account using the `usim get projects` command:
MacOS:
`USimCLI/mac/usim get projects`
In case you have more than one cloud project, you will need to "activate" the one corresponding with your perception tutorial project. If there is only one project, it is already activated, and you will not need to execute the command below (note: replace `<project-id>` with the id of your desired project).
* **Action**: Activate the relevant project:
* **:green_circle: Action**: Activate the relevant project:
MacOS:
`USimCLI/mac/usim activate project <project-id>`
Now that we have made sure the correct project is active, we can get a list of all the current and past runs for the project.
* **Action**: Use the `usim get runs` command to obtain a list of current and past runs:
* **:green_circle: Action**: Use the `usim get runs` command to obtain a list of current and past runs:
MacOS:
`USimCLI/mac/usim get runs`
Unity Simulation utilizes the ability to run simulation instances in parallel. If you enter a number larger than 1 for the number of instances in the _**Run in Unity Simulation**_ window, your run will be parallelized, and multiple simulation instances will simultaneously execute. You can view the status of all simulation instances using the `usim summarize run-execution <execution-id>` command. This command will tell you how many instances have succeeded, failed, have not run yet, or are in progress. Make sure to replace `<execution-id>` with the execution ID seen in your run list. In the above example, this ID would be `yegz4WN`.
* **Action**: Use the `usim summarize run-execution <execution-id>` command to observe the status of your execution nodes:
* **:green_circle: Action**: Use the `usim summarize run-execution <execution-id>` command to observe the status of your execution nodes:
At this point, we will need to wait until the execution is complete. Check your run with the above command periodically until you see a 1 for `Successes` and 0 for `In Progress`.
Given the relatively small size of our Scenario (1,000 Iterations), this should take less than 5 minutes.
* **Action**: Use the `usim summarize run-execution <execution-id>` command periodically to check the progress of your run.
* **Action**: When execution is complete, use the `usim download manifest <execution-id>` command to download the execution's manifest:
* **:green_circle: Action**: Use the `usim summarize run-execution <execution-id>` command periodically to check the progress of your run.
* **:green_circle: Action**: When execution is complete, use the `usim download manifest <execution-id>` command to download the execution's manifest:
* **Action**: Open the manifest file to check it. Make sure there are links to various types of output and check a few of the links to see if they work.
* **:green_circle: Action**: Open the manifest file to check it. Make sure there are links to various types of output and check a few of the links to see if they work.
### <aname="step-4">Step 4: Analyze the Dataset using Dataset Insights</a>
* **Action**: Open the Dataset Insights Jupyter notebook again, using the command below:
* **:green_circle: Action**: Open the Dataset Insights Jupyter notebook again, using the command below:
`docker run -p 8888:8888 -v <download path>/data:/data -t unitytechnologies/datasetinsights:latest`
* **Action**: Open a web browser and navigate to `http://localhost:8888` to open the Jupyter notebook.
* **Action**: Navigate to the `datasetinsights/notebooks` folder and open `Perception_Statistics.ipynb`.
* **Action**: In the `data_root = /data/<GUID>` line, the `<GUID>` part will be the location inside your `<download path>` where the data will be downloaded. Therefore, you can just remove it so as to have data downloaded directly to the path you previously specified:
* **:green_circle: Action**: Open a web browser and navigate to `http://localhost:8888` to open the Jupyter notebook.
* **:green_circle: Action**: Navigate to the `datasetinsights/notebooks` folder and open `Perception_Statistics.ipynb`.
* **:green_circle: Action**: In the `data_root = /data/<GUID>` line, the `<GUID>` part will be the location inside your `<download path>` where the data will be downloaded. Therefore, you can just remove it so as to have data downloaded directly to the path you previously specified:
<palign="center">
<imgsrc="Images/di_usim_1.png"/>
* **Action**: In the block of code titled "Unity Simulation [Optional]", uncomment the lines that assign values to variables, and insert the correct values, based on information from your Unity Simulation run.
* **:green_circle: Action**: In the block of code titled "Unity Simulation [Optional]", uncomment the lines that assign values to variables, and insert the correct values, based on information from your Unity Simulation run.
* **Action**: Return to your command-line interface and run the `usim inspect auth` command.
* **:green_circle: Action**: Return to your command-line interface and run the `usim inspect auth` command.
MacOS:
`USimCLI/mac/usim inspect auth`
The `access_token` you need for your Dataset Insights notebook is the access token shown by the above command, minus the `'Bearer '` part. So, in this case, we should input `0CfQbhJ6gjYIHjC6BaP5gkYn1x5xtAp7ZA9I003fTNT1sFp` in the notebook.
* **Action**: Copy the access token excluding the `'Bearer '` part to the corresponding field in the Dataset Insights notebook.
* **:green_circle: Action**: Copy the access token excluding the `'Bearer '` part to the corresponding field in the Dataset Insights notebook.
Once you have entered all the information, the block of code should look like the screenshot below (the actual values you input will be different):
* **Action**: Continue to the next code block and run it to download all the metadata files from the generated dataset. This includes JSON files and logs but does not include images (which will be downloaded later).
* **:green_circle: Action**: Continue to the next code block and run it to download all the metadata files from the generated dataset. This includes JSON files and logs but does not include images (which will be downloaded later).
You will see a progress bar while the data downloads:
The next couple of code blocks (under "Load dataset metadata") analyze the downloaded metadata and display a table containing annotation-definition-ids for the various metrics defined in the dataset.
* **Action**: Once you reach the code block titled "Built-in Statistics", make sure the value assigned to the field `rendered_object_info_definition_id` matches the id displayed for this metric in the table output by the code block immediately before it. The screenshot below demonstrates this (note that your ids might differ from the ones here):
* **:green_circle: Action**: Once you reach the code block titled "Built-in Statistics", make sure the value assigned to the field `rendered_object_info_definition_id` matches the id displayed for this metric in the table output by the code block immediately before it. The screenshot below demonstrates this (note that your ids might differ from the ones here):
text="Scenarios control the execution flow of your simulation by applying randomization parameters. Make sure to always have only one scenario active within your scene."/>
text="Scenarios control the execution flow of your simulation by applying randomization parameters. Make sure to always have only one scenario active within your scene."/>
<Toggle label="Quit On Complete" tooltip="Quit the application when the scenario completes" binding-path="quitOnComplete" style="margin-top:5px"/>
<editor:PropertyField
binding-path="constants"
tooltip="A list of parameters for this scenario that will be JSON serialized."/>
<Foldout style="padding-left: 16px" text="Constants" name="constants-list" tooltip="A list of parameters for this scenario that will be JSON serialized in the configuration file."/>
/// The total number of iterations to run a scenario for
/// The total number of iterations to run a scenario for. At the start of each iteration, the timings for all Perception Cameras will be reset.
[Tooltip("The total number of iterations to run a scenario for. At the start of each iteration, the timings for all Perception Cameras will be reset.")]
/// The number of Unity Simulation instances assigned to executed this scenario
/// The number of Unity Simulation instances assigned to execute this scenario. The total number of iterations (N) will be divided by the number of instances (M), so each instance will run for N/M iterations.
[Tooltip("The number of Unity Simulation instances assigned to execute this scenario. The total number of iterations (N) will be divided by the number of instances (M), so each instance will run for N/M iterations.")]
/// The Unity Simulation instance index of the currently executing worker
/// The Unity Simulation instance index of the currently executing worker.
[Tooltip("The Unity Simulation instance index of the currently executing worker.")]
The Perception package provides a toolkit for generating large-scale datasets for perception-based machine learning, training and validation. It is focused on capturing ground truth for Camera-based use cases. In the future, the Perception package will include other types of sensors and machine learning tasks.
[Quick Installation Instructions](SetupSteps.md)
[Perception Tutorial](Tutorial/TUTORIAL.md)
## Preview package
This package is available as a preview, so it is not ready for production use. The features and documentation in this package might change before it is verified for release.
## Example projects using Perception
### SynthDet
<imgsrc="images/synthdet.png"/>
[SynthDet](https://github.com/Unity-Technologies/SynthDet) is an end-to-end solution for training a 2D object detection model using synthetic data.
### Unity Simulation Smart Camera example
<imgsrc="images/smartcamera.png"/>
The [Unity Simulation Smart Camera Example](https://github.com/Unity-Technologies/Unity-Simulation-Smart-Camera-Outdoor) illustrates how Perception could be used in a smart city or autonomous vehicle simulation. You can generate datasets locally or at scale in [Unity Simulation](https://unity.com/products/unity-simulation).
## Package contents
|Feature|Description|
|---|---|
|[Labeling](GroundTruthLabeling.md)|A component that marks a GameObject and its descendants with a set of labels|
|[LabelConfig](GroundTruthLabeling.md#label-config)|An asset that defines a taxonomy of labels for ground truth generation|
|[Perception Camera](PerceptionCamera.md)|Captures RGB images and ground truth from a [Camera](https://docs.unity3d.com/Manual/class-Camera.html).|
|[DatasetCapture](DatasetCapture.md)|Ensures sensors are triggered at proper rates and accepts data for the JSON dataset.|
|[Randomization (Experimental)](Randomization/Index.md)|The Randomization tool set lets you integrate domain randomization principles into your simulation.|
## Known issues
* The Linux Editor 2019.4.7f1 and 2019.4.8f1 might hang when importing HDRP-based Perception projects. For Linux Editor support, use 2019.4.6f1 or 2020.1
Mohsen Kamalzadeh
4 年前