simple_sequence.h

namespace onnx_light

Alias that makes onnx-light headers compatible with code that references ONNX_LIGHT_NAMESPACE (the macro used in the standard onnx package).

Set to ONNX_LIGHT_NAMESPACE so both names resolve to the same namespace.

Symbol-visibility attribute for the public onnx-light C++ API.

Defined as empty because onnx-light does not require explicit __declspec(dllexport) or __attribute__((visibility("default"))) annotations — visibility is controlled at the shared-library level. The macro is provided so that vendored ONNX headers that decorate their declarations with ONNX_API compile without modification.

Namespace alias so that ONNX C++ code (and consumers such as onnxruntime) that refers to the literal onnx namespace — rather than the ONNX_NAMESPACE macro — resolves to the onnx-light namespace. The standard onnx package lives in namespace onnx; onnx-light uses onnx_light (via ONNX_LIGHT_NAMESPACE), so this alias keeps onnx-light a true drop-in. It is only introduced when the onnx-light namespace differs from onnx.

namespace onnx_kernels

struct Sequence

#include <simple_sequence.h>

Sequence — minimal runtime tensor sequence used by backend test cases and reference kernel implementations.

Companion to :cpp:struct:Tensor: where Tensor carries a single tensor value, Sequence carries an ordered list of tensors that share a common element type. Sequence is intentionally separate from TensorProto / SequenceProto and from :cpp:class:onnx_optim::OptimSequence: it is the runtime value of a sequence-typed graph edge (analogous to Tensor being the runtime value of a tensor-typed edge), without any protobuf dependency.

The struct owns its underlying Tensor elements: copying or destroying the Sequence copies or destroys its elements too.

Public Functions

Sequence() = default

inline Sequence(std::string n, int32_t et, std::vector<Tensor> v)

inline std::size_t size() const noexcept

Number of tensors in the sequence.

inline bool empty() const noexcept

true when the sequence contains no tensors.

inline const Tensor &at(std::size_t i) const

Random access to the i-th tensor; throws std::out_of_range if i is out of bounds.

inline Tensor &at(std::size_t i)

Public Members

std::string name

Optional name of the sequence (input/output name in the test model). May be left empty for intermediate values.

int32_t elem_type = 0

Element data type shared by every tensor stored in values, expressed as a DataType integer value. Equals DataType::UNDEFINED (0) when values is empty and the element type cannot be inferred.

std::vector<Tensor> values

Tensor elements of the sequence, in order. All elements must share elem_type; element shapes may differ between elements.