Namespace Barracuda
Classes
ArrayTensorData
BarracudaTextureUtils
BarracudaWorkerFactory
BLASPluginFactory
CompareOps
ComputeInfo
ComputeKernelLibrary
ComputeOps
ComputeTensorData
ComputeVarsWithSharedModel
CSharpBLAS
D
DefaultTensorAllocator
DefaultVars
GenericVars
GenericVarsWithPreallocation
GenericVarsWithReuse
GenericWorker
JSONTensor
JSONTensorShape
JSONTestSet
Layer
MathfEx
Model
Model.ImporterWarning
ModelAnalyzer
ModelBuilder
ModelLoader
ModelMetadataExtensions
ModelWriter
NNModel
NNModelEditor
Asset Importer Editor of NNModel (the serialized file generated by ONNXModelImporter)
NNModelImporter
Asset Importer of barracuda models.
ONNXModelImporter
Asset Importer of ONNX models, this will convert to barracuda NN model.
ONNXModelImporter.VariableTensor
ONNXModelImporterEditor
Asset Importer Editor of ONNX models
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
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
ONNXModelImporter.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
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
WorkerFactory.Device
Supported device type
WorkerFactory.Type
Backend type