OnnxModel.h 文件参考

#include "common/Export.h"
#include "common/Result.h"
#include "tensor/OnnxStorage.h"
#include <cstddef>
#include <cstdint>
#include <memory>
#include <span>
#include <string>
#include <vector>

浏览源代码.

类
struct	eve::tensor::OnnxTensor
	Owning ONNX boundary tensor: row-major little-endian bytes and exact integer shape. 更多...
struct	eve::tensor::OnnxNamedTensor
	Owning named feed/output value. 更多...
struct	eve::tensor::OnnxRunOptions
	Per-call deterministic RNG and optional strict finite-output diagnostic. 更多...
struct	eve::tensor::OnnxGpuResult
	Owning GPU execution output and completed dispatch count. 更多...
struct	eve::tensor::OnnxModelInfo
	Owning admission report; unsupported nodes remain inspectable but cannot execute. 更多...
class	eve::tensor::OnnxModel
	Native ONNX import and CPU/GPU execution using tensor kernels, without ONNX Runtime. 更多...

命名空间
namespace	eve
	Build metadata (engine git commit, build time, third-party version).
namespace	eve::tensor

枚举
enum class	eve::tensor::OnnxElement : int {   eve::tensor::Float32 = 1 , eve::tensor::UInt8 = 2 , eve::tensor::Int8 = 3 , eve::tensor::Int32 = 6 ,   eve::tensor::Int64 = 7 , eve::tensor::Bool = 9 }
	ONNX wire element types; distinct from block-quantized Tensor storage. 更多...