Tensors, model abstraction, ONNX Runtime inference and Python training drivers used across mne-cpp. More...
Classes | |
| class | MlModel |
| Backend-agnostic inference interface: load, predict, save plus model/task descriptors. More... | |
| class | MlOnnxModel |
MlModel backend that runs .onnx graphs through ONNX Runtime with a cached CPU session. More... | |
| class | MlTensor |
| N-dimensional row-major float32 tensor with shared-buffer storage, Eigen Map accessors and a non-owning view mode. More... | |
| class | MLTrainer |
| Launches Python training scripts via UTILSLIB::PythonRunner with automatic venv handling and prerequisite checks. More... | |
Enumerations | |
| enum class | MlBackend { OnnxRuntime , BuiltIn } |
| enum class | MlDataType { Float32 , Float64 , Int64 } |
| enum class | MlTaskType { Classification , Regression , FeatureExtraction } |
Functions | |
| MLSHARED_EXPORT const char * | buildDateTime () |
| MLSHARED_EXPORT const char * | buildHash () |
| MLSHARED_EXPORT const char * | buildHashLong () |
Tensors, model abstraction, ONNX Runtime inference and Python training drivers used across mne-cpp.
|
strong |
Available ML back-end engines.
| Enumerator | |
|---|---|
| OnnxRuntime | |
| BuiltIn | |
Definition at line 39 of file ml_types.h.
|
strong |
Supported data types for tensors.
| Enumerator | |
|---|---|
| Float32 | |
| Float64 | |
| Int64 | |
Definition at line 45 of file ml_types.h.
|
strong |
ML task categories.
| Enumerator | |
|---|---|
| Classification | |
| Regression | |
| FeatureExtraction | |
Definition at line 51 of file ml_types.h.
| const char * MLLIB::buildDateTime | ( | ) |
Returns build date and time.
Definition at line 30 of file ml_global.cpp.
| const char * MLLIB::buildHash | ( | ) |
Returns abbreviated build git hash.
Definition at line 34 of file ml_global.cpp.
| const char * MLLIB::buildHashLong | ( | ) |
Returns full build git hash.
Definition at line 38 of file ml_global.cpp.