RunYOLO.cs

using System.Collections.Generic;
using Unity.Sentis;
using UnityEngine;
using UnityEngine.UI;
using UnityEngine.Video;

/*
 *  YOLO inference script
 *  =====================
 * 
 * Place this script on the Main Camera.
 * 
 * Place the yolov7-tiny.sentis file and a *.mp4 video file in the Assets/StreamingAssets folder
 * 
 */


public class RunYOLO : MonoBehaviour
{
    const string modelName = "yolov7-tiny.sentis";
    const string videoName = "giraffes.mp4";
    // Link the classes.txt here:
    public TextAsset labelsAsset;
    // Create a Raw Image of size 640x640 and link it here:
    public RawImage displayImage;
    // Link to a bounding box texture here:
    public Sprite boxTexture;
    // Link to the font for the labels:
    public Font font;

    private Transform displayLocation;
    private Model model;
    private IWorker engine;
    private string[] labels;
    private RenderTexture targetRT;
    const BackendType backend = BackendType.GPUCompute;
    private const int imageWidth = 640;
    private const int imageHeight = 640;

    private VideoPlayer video;

    //bounding box data
    public struct BoundingBox
    {
        public float centerX;
        public float centerY;
        public float width;
        public float height;
        public string label;
        public float confidence;
    }
    
    void Start()
    {
        Application.targetFrameRate = 60;
        Screen.orientation = ScreenOrientation.LandscapeLeft;
        
        //Parse neural net labels
        labels = labelsAsset.text.Split('\n');

        //Load model
        model = ModelLoader.Load(Application.streamingAssetsPath + "/" + modelName);

        targetRT = new RenderTexture(imageWidth, imageHeight, 0);

        //Create image to display video
        displayLocation = displayImage.transform;

        //Create engine to run model
        engine = WorkerFactory.CreateWorker(backend, model);

        SetupInput();
    }
    void SetupInput()
    {
        video = gameObject.AddComponent<VideoPlayer>();
        video.renderMode = VideoRenderMode.APIOnly;
        video.source = VideoSource.Url;
        video.url = Application.streamingAssetsPath + "/" + videoName;
        video.isLooping = true;
        video.Play();
    }

    private void Update()
    {
        ExecuteML();

        if (Input.GetKeyDown(KeyCode.Escape))
        {
            Application.Quit();
        }
    }

    public void ExecuteML()
    {
        ClearAnnotations();

        if (video && video.texture)
        {
            float aspect = video.width * 1f / video.height;
            Graphics.Blit(video.texture, targetRT, new Vector2(1f / aspect, 1), new Vector2(0, 0));
            displayImage.texture = targetRT;
        }
        else return;

        using var input = TextureConverter.ToTensor(targetRT, imageWidth, imageHeight, 3);
        engine.Execute(input);

        //Read output tensors
        var output = engine.PeekOutput() as TensorFloat;
        output.MakeReadable();

        //Draw the bounding boxes
        for (int n = 0; n < output.shape[0]; n++)
        {
            var box = new BoundingBox
            {
                centerX = (output[n, 1] + output[n, 3]) / 2 - 320,
                centerY = (output[n, 2] + output[n, 4]) / 2 - 320,
                width = output[n, 3] - output[n, 1],
                height = output[n, 4] - output[n, 2],
                label = labels[(int)output[n, 5]],
                confidence = Mathf.FloorToInt(output[n, 6] * 100 + 0.5f)
            };
            DrawBox(box);
        }
    }

    public void DrawBox(BoundingBox box)
    {
        Color color = Color.yellow;

        GameObject panel = new GameObject("ObjectBox");
        panel.AddComponent<CanvasRenderer>();
        Image img = panel.AddComponent<Image>();
        img.color = color;
        img.sprite  = boxTexture;
        
        panel.transform.SetParent(displayLocation, false);
        panel.transform.localPosition = new Vector3(box.centerX, -box.centerY);

        RectTransform rt = panel.GetComponent<RectTransform>();
        rt.sizeDelta = new Vector2(box.width, box.height);

        //add class label
        var text = new GameObject("ObjectLabel");
        text.AddComponent<CanvasRenderer>();
        Text txt = text.AddComponent<Text>();
        text.transform.SetParent(panel.transform, false);
        txt.font = font;
        txt.text = box.label + " (" + box.confidence + "%)";
        txt.color = color;
        txt.fontSize = 40;
        txt.horizontalOverflow = HorizontalWrapMode.Overflow;
        RectTransform rt2 = text.GetComponent<RectTransform>();
        rt2.offsetMin = new Vector2(20, rt2.offsetMin.y);
        rt2.offsetMax = new Vector2(0, rt2.offsetMax.y);
        rt2.offsetMax = new Vector2(rt2.offsetMax.x, 30);
        rt2.offsetMin = new Vector2(rt2.offsetMin.x, 0);
        rt2.anchorMin = new Vector2(0,0);
        rt2.anchorMax = new Vector2(1, 1);

        img.sprite = boxTexture;
        img.type = Image.Type.Sliced;
    }

    public void ClearAnnotations()
    {
        foreach (Transform child in displayLocation) {
            Destroy(child.gameObject);
        }
    }

    private void OnDestroy()
    {
        engine?.Dispose();
    }
}