Layer output is non deterministic, i.e. may be different each time the layer is run e.g. Layers which use random number generation such as RandomUniform, Bernoulli, Multinomial These layers will not have outputs precalculated at import time for optimization passes

PixelShaderSingleton

Represents the compute kernel cache for backends that use GPU pixel shaders.

Random

Represents a pseudo-random number generator used by Sentis.

SharedArrayTensorData

Represents internal Tensor data backed by a managed array and shared between multiple tensors.

Tensor

Represents data in a multidimensional array-like structure.

TensorExtensions

Provides extension methods for tensors.

TensorFloat

Represents data in a multidimensional array-like structure of floats.

TensorInt

Represents data in a multidimensional array-like structure of ints.

TextureConverter

Provides methods for converting between textures and tensors.

TextureTensorData

Represents the data storage for a Tensor as a render texture, for backends that use GPU pixel shaders.

Sentis packs the tensor data into the pixels of an ARGB float4 texture.

Sentis chooses a single tensor dimension as the blocked axis, across which data is chunked in float4 blocks.

Texture dimensions don't map directly to tensor dimensions. Sentis creates the texture with dimensions large enough for the data, and pixel shaders index the data based on both the tensor and texture dimensions.

WaitForCompletion

Provides methods for suspending the execution of coroutines until the worker completes execution on a device, and Sentis downloads the contents of the specified tensor to the main CPU memory.

You usually shouldn't use WaitForCompletion, unless you access tensor contents on the CPU.

You can only use WaitForCompletion with a yield statement in coroutines.

WorkerExtensions

Provides extension methods for the IWorker interface.

WorkerFactory

Provides methods for instantiating workers and ops on given back ends.

Structs

Model.Input

Represents an input to a model.

Model.OpsetDescription

Represents an ONNX opset domain and version number.

SymbolicTensorDim

Represents a single dimension of a SymbolicTensorShape.

SymbolicTensorShape

Represents the shape of an input tensor, or the predicted shape of a tensor before Sentis executes.

TensorNDIterator

Represents a struct used to iterate over a TensorShape.

TensorShape

Represents the shape of a tensor.

TextureTransform

Represents settings for converting between textures and tensors.

Create an instance of TextureTransform using the constructor, then use the TextureTransform object as a parameter in TextureConverter methods.

For example: TextureTransform settings = new TextureTransform().SetDimensions(256, 256, 4).SetTensorLayout(TensorLayout.NHWC);

WorkerFactory.WorkerConfiguration

Represents the configuration for a WorkerFactory.

Specify inputs.
Schedule the work.
Get outputs.

Internally, IWorker translates the neural network from a Model into a set of operations, then sends the operations to the hardware device for asynchronous execution.

Use WorkerFactory.CreateWorker or Model.CreateWorker to create a new instance of a worker.

Namespace Unity.Sentis

Classes

Structs

Interfaces

Enums