* [Ref] Multinomial base file * [Ref] Add core & reference implementation reusing other ops * [Ref] Fix reference implementation, add missing parameters, add tests * [Core] Add opset13, register multinomial, add shape inference * [Ref][Core] Fix compile errors * [Ref][Core] Clang fix * [TEMPLATE] Remove bf16, f16, f64 types * [TEMPLATE] Remove incorrect input types for 'input' parameter * [Ref][Tests] Remove deleted test types * [Ref] Fix & optimize shape inference * [PT FE] Apply suggestions from review * [Template] Migrate to new API * [Core] Add a clause for dynamic input in shape inference * [Tests] Add missing type_prop test (?) * Update multinomial_shape_inference.hpp * Update multinomial.hpp * [Ref] Fix build issues * [Ref] Fix clang and style * [Ref] Fix tests without replacement * [Ref] Fix with_replacement sampling error * [Ref] Remove debugging artifacts * [Ref] Cast to 64-bit size for 32-bit systems * Update multinomial.hpp * [Ref] Add missing type_prop tests, add shape inference tests * Update multinomial.cpp * Update multinomial_shape_inference_test.cpp * Update multinomial.cpp * Update multinomial.hpp * [Ref] Fix compilation errors from shape inference test * [Ref] Fix compilation error of type_prop, apply recommendations from review * [Ref] Add multiple shape inference tests * [Ref] Change TEST to TEST_F, add more type_prop tests * [Ref] Clang fixes * [Ref] Fix shape inference tests with mismatching args * [Ref] Fix remaining type_prop errors * [Ref] Replace HostTensor with normal Tensor in shape inference tests * Update opset.cpp * [Ref] Possible fix for 'function empty' error * [Ref] Add a cast to remove conversion warning * [Ref] Add conformance test of Multinomial * [Ref] Match style of conf test to the remaining tests * Update single_op_graph.cpp
OpenVINO™ Core Components
This section provides references and information about OpenVINO core components.
bindings/ // OpenVINO bindings
cmake/ // Common cmake scripts
common/ // Common components
core/ // OpenVINO core component provides model representation, operations and other core functionality
frontends/ // OpenVINO frontends
inference/ // Provides API for model inference
plugins/ // OpenVINO plugins
tests/ // A backed of tests binaries for core and plugins
OpenVINO Runtime library
OpenVINO Runtime is a common OpenVINO library which provides functionality for Neural Network inference. The library includes next parts:
flowchart LR
subgraph openvino [openvino library]
core
inference
transformations[Common transformations]
lp_transformations[LP transformations]
frontend_common
style frontend_common fill:#7f9dc0,stroke:#333,stroke-width:4px
style transformations fill:#3d85c6,stroke:#333,stroke-width:4px
style lp_transformations fill:#0b5394,stroke:#333,stroke-width:4px
style core fill:#679f58,stroke:#333,stroke-width:4px
style inference fill:#d7a203,stroke:#333,stroke-width:4px
end
- core is responsible for model representation, contains a set of supported OpenVINO operations and base API for model modification.
- inference provides the API for model inference on different accelerators.
- Transformations:
- common transformations - a set of common transformations which are used for model optimization
- low precision transformations - a set of transformations which are needed to optimize quantized models
- frontend_common provides frontend common API which allows to support frontends for different frameworks.
OpenVINO Frontends
OpenVINO Frontends allow to convert model from framework to OpenVINO representation.
Go to the Frontends page to get more information.
OpenVINO Plugins
OpenVINO Plugins provide support for hardware devices.
To get more information about supported OpenVINO Plugins, go to the Plugins page.
OpenVINO Bindings
OpenVINO provides bindings for different languages. To get the full list of supported languages, go to the bindings page.