Class ComputeTensorData
Represents data storage for a Tensor
as a compute buffer, for GPUCompute backend.
Inherited Members
Namespace: Unity.Sentis
Assembly: solution.dll
Syntax
public class ComputeTensorData : ITensorData, IDisposable
Constructors
Name | Description |
---|---|
ComputeTensorData(TensorShape, bool) | Initializes and returns an instance of |
ComputeTensorData(TensorShape, NativeTensorArray, int) | Initializes and returns an instance of |
Properties
Name | Description |
---|---|
buffer | The data storage as a compute buffer. |
deviceType | On what device backend are the data elements stored. |
maxCapacity | The maximum count of the stored data elements. |
shape | The shape of the tensor using this data as a |
Methods
Name | Description |
---|---|
Clone() | Returns a deep copy of the internal storage. |
CompleteAllPendingOperations() | Blocking call to make sure that internal data is correctly written to and available for CPU read back. |
Dispose() | Disposes of the |
Download<T>(int, int) | Returns a contiguous block of data from internal storage. |
~ComputeTensorData() | Finalizes the |
IsReadbackRequestDone() | Checks if asynchronous readback request is done. |
Pin(Tensor, bool) | Moves the tensor into GPU memory on the GPUCompute backend device. |
ReadbackRequest(Action<bool>) | Schedules asynchronous readback of the internal data. |
ReadbackRequestAsync() | Schedules awaitable asynchronous readback of the internal data. See AsyncReadbackRequest for more info |
Reserve(int) | Reserves memory for |
ToString() | Returns a string that represents the |
Upload<T>(NativeArray<T>, int, int) | Uploads a contiguous block of tensor data to internal storage. |