[][src]Module tract_onnx::prelude

Re-exports

pub use crate::onnx;

Modules

compact
dsl
order

Evaluation order for nodes.

tract_itertools

Extra iterator adaptors, functions and macros.

tract_linalg
tract_ndarray

The ndarray crate provides an n-dimensional container for general elements and for numerics.

tract_num_traits

Numeric traits for generic mathematics

translator

Macros

tvec

Structs

Arc

A thread-safe reference-counting pointer. 'Arc' stands for 'Atomically Reference Counted'.

BaseNode

A Node in an Model.

Blob
InferenceFact

Partial information about a tensor.

InletId

Identifier for a node input in the graph.

ModelImpl

Main model class

ModelPatch

A change to apply to a model.

OutletFact

Information for each outlet of a node

OutletId

Identifier for a node output in the graph.

ShapeFact

Fully determined dimension of a tensor.

SimplePlan
SimpleState
StreamFact

Streaming information for a streamed tensor.

Tensor

Tensor is a concrete tensor in tract.

TractError

The Error type.

TypedFact

Fully determined tensor information for TypedModel.

Enums

DatumType
TDim
TractErrorKind

The kind of an error.

Traits

Datum
Fact

Type information about a tensor: shape, and element type, in various state of determination.

Framework

A Framework that translate its model to tract core model.

InferenceModelExt
IntoArcTensor

Convenient conversion to Arc.

IntoTensor

Convenient conversion to Tensor.

Model

Common methods for all variants of model.

ModelDsl

Extensions on ModelImpl to explore and build graph models more easily.

ModelDslConst

Extension to add constants to model that tolerates them.

ModelSpecialOps
ModelWireNode
Op

A base operation

TractResultExt

Additional methods for Result, for easy interaction with this crate.

TypedOp

Functions

arr4
eval_order

Find an evaluation order for a model, using its default inputs and outputs as boundaries.

rctensor0
rctensor1
rctensor2
rctensor3
rctensor4
tensor0
tensor1
tensor2
tensor3
tensor4

Type Definitions

InferenceModel

A model with partially types and shapes, as produced by parsing ONNX or Tensorflow graphs.

InferenceSimplePlan

An execution plan for InferenceModel.

Node
RunnableModel

A runnable model with fixed inputs and outputs.

TVec

A Smallvec instantiation with 4 embeddable values.

TractResult

Convenient wrapper around std::Result.

TypedModel

A model with completely determined types and shapes.

TypedModelPatch

A ModelPatch for TypedModel.

TypedNode

Node for TypedModel graph

TypedRunnableModel

A runnable TypedModel (new name for SimplePlan).

TypedSimplePlan

An execution plan for TypedModel.

TypedSimpleState

An execution state for TypedModel.