tensor/utils.h

Tensor-domain schema helpers, including onnx_light::resizeShapeInference() and onnx_light::gridSampleShapeInference().

Declares tensor-operator schema and shape-inference helpers.

This header exposes helper routines used by tensor-domain operators such as Resize and GridSample, including opset-specific inference entry points.

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.

Enums

enum class KeepAspectRatioPolicy : std::uint8_t

Values:

enumerator STRETCH

enumerator NOT_LARGER

enumerator NOT_SMALLER

Functions

void resizeShapeInference(InferenceContext &ctx)

void gridSampleShapeInference(InferenceContext &ctx)

void resizeShapeInferenceHelper(const TensorShapeProto &input_shape, const std::vector<float> &scales_data, TensorShapeProto *output_shape)

void resizeShapeInferenceHelper(const TensorShapeProto &input_shape, const std::vector<int64_t> &sizes_data, TensorShapeProto *output_shape)

void resizeShapeInference_opset7_to_10(InferenceContext &ctx)

void resizeShapeInference_opset11_to_12(InferenceContext &ctx)

void resizeShapeInference_opset13_to_18(InferenceContext &ctx)

void resizeShapeInference_opset18_to_19(InferenceContext &ctx)

void resizeShapeInferenceHelper_opset7_to_10(const TensorShapeProto &input_shape, const std::vector<float> &scales_data, TensorShapeProto *output_shape)

void KeepAspectRatioHelper(KeepAspectRatioPolicy policy, const TensorShapeProto &input_shape, const std::vector<int64_t> &axes, std::vector<int64_t> &sizes_data)

std::function<void(OpSchema&)> PadDocGenerator(const char *description, const char *mode_description, std::vector<std::string> op_schema = OpSchema::all_tensor_types_ir4(), std::string op_schema_description = "Constrain input and output types to all tensor types.")

Variables

const char *NonZero_ver9_doc

const char *Transpose_doc