Note

Sentis is now called Inference Engine. The documentation has moved to https://docs.unity3d.com/Packages/com.unity.ai.inference@latest. Refer to the new location for the latest updates and guidance. Make sure to update your bookmarks and references accordingly.

Use a command buffer

You can use a command buffer to create a queue of Sentis commands, which can then be executed on the GPU at a later time.

Follow these steps:

  1. Create or get an empty command buffer.
  2. Create a worker with the BackendType.GPUCompute backend type.
  3. In a Unity event function, for example OnRenderImage, add Sentis methods to the command buffer.
  4. Use Graphics.ExecuteCommandBuffer to execute the command buffer.

To add commands to the command buffer, do any of the following:

For example, the following code creates and executes a command buffer queue. This queue first converts a render texture to an input tensor, then runs the model, and finally converts the output tensor back to a render texture.

// Create a worker that uses the GPUCompute backend type
worker = new Worker(ModelLoader.Load(modelAsset), BackendType.GPUCompute);

//...

// Add model execution command buffer that runs the model using the input tensor
commandBuffer.ScheduleWorker(worker, inputs);

Build the CommandBuffer once, update the input every frame and execute the CommandBuffer. This reduces the scheduling time by half.

Tensor<float> input0 = new Tensor<float>(new TensorShape(1));
Model model;
CommandBuffer cb;
Worker worker;

void Start()
{
    worker = new Worker(model, BackendType.GPUCompute);

    worker.SetInput("input0", input0);

    cb = new CommandBuffer();
    cb.ScheduleWorker(worker);
}

void Update()
{
    // modify input0
    input0.Upload(new float[] { Time.deltaTime });
    Graphics.ExecuteCommandBuffer(cb);
}

For more information, refer to: