Namespace Barracuda
Classes
ArrayTensorData
BarracudaTextureUtils
BarracudaWorkerFactory
BLASPluginFactory
CompareOps
ComputeInfo
ComputeKernelLibrary
ComputeOps
ComputeShaderSingleton
ComputeTensorData
ComputeVarsWithSharedModel
CSharpBLAS
D
DefaultTensorAllocator
DefaultVars
DeprecatedWorkerExtensions
GenericVars
GenericVarsWithPreallocation
GenericVarsWithReuse
GenericWorker
JSONTensor
JSONTensorShape
JSONTestSet
Layer
MathfEx
MatrixUtils
Model
Model.ImporterWarning
ModelAnalyzer
ModelBuilder
ModelLoader
ModelMetadataExtensions
ModelOptimizer
ModelWriter
NNModel
NNModelData
NNModelEditor
Asset Importer Editor of NNModel (the serialized file generated by ONNXModelImporter)
NNModelExtensions
NNModelImporter
Asset Importer of barracuda models.
OnnxImportException
OnnxLayerImportException
ONNXLayout
ONNXModelImporter
Asset Importer for Open Neural Network Exchange (ONNX) files. For more information about ONNX file format see: https://github.com/onnx/onnx
ONNXModelImporterEditor
Asset Importer Editor of ONNX models
ONNXModelTensors
ONNXNodeWrapper
PrecompiledComputeOps
RawTestSet
RecurrentState
Object that represent memory (recurrent state) between the executions of a given model.
ReferenceComputeOps
ReferenceCPUOps
ReferenceCPUOps.Seed
SharedArrayTensorData
SharedComputeTensorData
StatsOps
StringCache
Tensor
TensorCachingAllocator
TensorCachingByShapeAllocator
TensorExtensions
TensorOperatorNewAllocator
TestSet
TestSetLoader
TextureAsTensorData
TextureFormatUtils
UnsafeArrayCPUOps
UnsafeArrayTensorData
VerboseOps
WaitForCompletion
Suspends the coroutine execution until worker has completed execution on a device and
contents of the specified tensor are downloaded to the main CPU memory.
WaitForCompletion is not necessary and should NOT be used, unless tensor contents are accessed on CPU!
WaitForCompletion can only be used with a yield statement in coroutines.
WorkerExtensions
WorkerFactory
Factory to create worker that executes specified model on a particular device (GPU, CPU, etc) using particular backend.
See IWorker for usage of the worker itself.
Structs
ComputeFunc
ComputeFunc.TensorDecl
ComputeKernel
ComputeKernelLibrary.Entry
ComputeKernelLibrary.StrictDimensions
Layer.DataSet
Model.Input
Model.Memory
ONNXTensor
TensorShape
TensorShape are immutable representation of a Tensor dimensions and rank. At the moment a TensorShape is always of rank 4 and channels last ie B,H,W,C. However an axis can be a size 1. For example a tensor without spatial information will be B,1,1,C
VariableTensor
Interfaces
BLASPlugin
IModelCompiler
Interfaces for model compiler
IOps
Interfaces for backend implementers see ModelBuilder.cs for detail on layers.
ITensorAllocator
Interfaces for tensor allocator
ITensorData
Interface for device dependent representation of Tensor data.
IVars
Interfaces for variables
IWorker
Public interface for Workers. A worker is able to schedule models execution for a given backend.
Use WorkerFactory to instantiate a worker.
Enums
BarracudaWorkerFactory.Flags
Layer.Activation
Layer.AutoPad
Layer.Type
TextureAsTensorData.Flip
TextureAsTensorData.InterpretColorAs
TextureAsTensorData.InterpretDepthAs
VariableTensor.Layout
WorkerFactory.Device
Supported device type
WorkerFactory.Type
Backend type