Crate ort

---

ort is a Rust binding for ONNX Runtime. For information on how to get started with ort, see https://ort.pyke.io/introduction.

Re-exports

• pub use ort_sys as sys;

Macros

• inputs
  Construct the inputs to a session from an array or named map of values.

Structs

• ACLExecutionProvider
• Allocator
  An ONNX Runtime allocator, used to manage the allocation of crate::Values.
• ArmNNExecutionProvider
• CANNExecutionProvider
• CPUExecutionProvider
• CUDAExecutionProvider
• CoreMLExecutionProvider
• DirectMLExecutionProvider
• DynMapValueType
• DynSequenceValueType
• DynTensorValueType
• DynValueTypeMarker
  The dynamic type marker, used for values which can be of any type.
• Environment
• EnvironmentBuilder
  Struct used to build an Environment.
• EnvironmentGlobalThreadPoolOptions
• InMemorySession
  A Session where the graph data is stored in memory.
• Input
  Information about a Session input.
• IoBinding
  Enables binding of session inputs and/or outputs to pre-allocated memory.
• KernelAttributes
• KernelContext
• MapValueType
• MemoryInfo
• ModelMetadata
  Container for model metadata, including name & producer information.
• NNAPIExecutionProvider
• OneDNNExecutionProvider
• OpenVINOExecutionProvider
• OperatorDomain
• OperatorInput
• OperatorOutput
• Output
  Information about a Session output.
• QNNExecutionProvider
• ROCmExecutionProvider
• RunOptions
  A structure which can be passed to Session::run_with_options to allow terminating/unterminating a session inference run from a different thread.
• SequenceValueType
• Session
  An ONNX Runtime graph to be used for inference.
• SessionBuilder
  Creates a session using the builder pattern.
• SessionOutputs
  The outputs returned by a crate::Session inference call.
• SharedSessionInner
  Holds onto an ort_sys::OrtSession pointer and its associated allocator.
• TVMExecutionProvider
• TensorRTExecutionProvider
• Value
  A Value contains data for inputs/outputs in ONNX Runtime graphs. Values can be a Tensor, Sequence (aka array/vector), or Map.
• ValueRef
  A temporary version of a Value with a lifetime specifier.
• ValueRefMut
  A mutable temporary version of a Value with a lifetime specifier.
• XNNPACKExecutionProvider

Enums

• AllocationDevice
  Represents possible devices that have their own device allocator.
• AllocatorType
  Execution provider allocator type.
• ArenaExtendStrategy
  The strategy for extending the device memory arena.
• CANNExecutionProviderImplementationMode
• CANNExecutionProviderPrecisionMode
• CUDAExecutionProviderCuDNNConvAlgoSearch
  The type of search done for cuDNN convolution algorithms.
• Error
  An enum of all errors returned by ORT functions.
• ErrorInternal
  Error details when ONNX C API returns an error.
• ExecutionProviderDispatch
  Execution provider container. See the ONNX Runtime docs for more info on execution providers. Execution providers are actually registered via the functions crate::SessionBuilder (per-session) or EnvironmentBuilder (default for all sessions in an environment).
• FetchModelErrorfetch-models
  Error from downloading pre-trained model from the ONNX Model Zoo.
• GraphOptimizationLevel
  ONNX Runtime provides various graph optimizations to improve performance. Graph optimizations are essentially graph-level transformations, ranging from small graph simplifications and node eliminations to more complex node fusions and layout optimizations.
• MemoryType
  Memory types for allocated memory.
• QNNExecutionProviderPerformanceMode
• SessionInputValue
• SessionInputs
  The inputs to a crate::Session::run call.
• TVMExecutorType
• TVMTuningType
• TensorElementType
  Enum mapping ONNX Runtime’s supported tensor data types.
• ValueType
  The type of a Value, or a session input/output.

Constants

• MINOR_VERSION
  The minor version of ONNX Runtime used by this version of ort.

Traits

• ArrayExtensionsndarray
  Trait extending ndarray::ArrayBase with useful tensor operations.
• DowncastableTarget
  Represents a type that a DynValue can be downcast to.
• ExecutionProvider
  ONNX Runtime works with different hardware acceleration libraries through its extensible Execution Providers (EP) framework to optimally execute the ONNX models on the hardware platform. This interface enables flexibility for the AP application developer to deploy their ONNX models in different environments in the cloud and the edge and optimize the execution by taking advantage of the compute capabilities of the platform.
• IntoTensorElementType
  Trait used to map Rust types (for example f32) to ONNX tensor element data types (for example Float).
• Kernel
• MapValueTypeMarker
• Operator
• SequenceValueTypeMarker
• TensorValueTypeMarker
• ValueTypeMarker
  Marker trait used to determine what operations can and cannot be performed on a Value of a given type.

Functions

• api
  Returns a pointer to the global ort_sys::OrtApi object.
• get_environment
  Gets a reference to the global environment, creating one if an environment has been committed yet.
• init
  Creates an ONNX Runtime environment.
• init_from
  Creates an ONNX Runtime environment, dynamically loading ONNX Runtime from the library file (.dll/.so/.dylib) specified by path.

Type Aliases

• DynMap
• DynMapRef
• DynMapRefMut
• DynSequence
• DynSequenceRef
• DynSequenceRefMut
• DynTensor
• DynTensorRef
• DynTensorRefMut
• DynValue
  A dynamic value, which could be a Tensor, Sequence, or Map.
• InferShapeFn
• Map
• MapRef
• MapRefMut
• Result
  Type alias for the Result type returned by ORT functions.
• Sequence
• SequenceRef
• SequenceRefMut
• Tensor
• TensorRef
• TensorRefMut