Model Builder API #23223
Model Builder API #23223
Conversation
Supports creating a model programmatically using the ORT C or C++ API. Supports augmenting an existing model to add nodes.
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
include/onnxruntime/core/session/onnxruntime_session_options_config_keys.h
Fixed
Show fixed
Hide fixed
| #include "core/framework/error_code_helper.h" | ||
| #include "core/framework/execution_provider.h" | ||
| #include "core/session/abi_session_options_impl.h" | ||
| // #include "core/session/environment.h" |
Check notice
Code scanning / CodeQL
Commented-out code Note
include/onnxruntime/core/session/onnxruntime_session_options_config_keys.h
Outdated
Show resolved
Hide resolved
|
Is it possible to save out the model from the builder via the C API? It'll be a nice alternative to building ONNX models with raw protobufs in languages which don't have a native ONNX library. |
You can use the SessionOption that's typically used to save the optimized ONNX model. onnxruntime/include/onnxruntime/core/session/onnxruntime_c_api.h Lines 909 to 910 in 6e76179 Caveat is that does not currently support saving tensors created with CreateTensorWithDataAsOrtValue or CreateTensorWithDataAndDeleterAsOrtValue, but could be updated to do so if required. |
Is the optimized model one which has had op fusion and other passes done so it's no longer using ONNX standard ops everywhere, or is that a different process? |
You can specify the optimization level. If you keep it to level 1 (GraphOptimizationLevel.ORT_ENABLE_BASIC) it will only use standard ONNX ops. onnxruntime/include/onnxruntime/core/session/onnxruntime_c_api.h Lines 343 to 345 in a3833a5 onnxruntime/include/onnxruntime/core/session/onnxruntime_c_api.h Lines 1020 to 1029 in a3833a5 https://onnxruntime.ai/docs/performance/model-optimizations/graph-optimizations.html |
* Pass ORT_API_VERSION to `OrtApiBase::GetApi()` Also removes the inclusion of onnx.pb.h header. * Add third_party/onnxruntime_headers Import https://github.com/microsoft/onnxruntime/tree/main/include Commit is based on microsoft/onnxruntime#23223 * Use ORT Model Builder API * Refactor scoped ORT type ptr 1. Rename to ScopedOrtTypePtr 2. Use macros 3. Introduce `operator T*()` 4. Introduce `Release()` method 5. Rename `get_ptr()` to `Get()` 6. Rename `get_pptr()` to `GetAddressOf()` * Remove ONNX Runtime headers from third_party/microsoft_dxheaders
@skottmckay , Saving tensors created with |
- enforce 128 byte minimum for tensors with external data to avoid shape inferencing issues - update unit tests to use 128 byte initializer so external data can be tested - support saving initializer with in-memory external data to ONNX model by copying into TensorProto's raw_data property.
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
Exclude model editor API funcs from minimal build. They require Graph::Resolve and therefore need a full build.
…uct by adding a dummy field.
Cleanup some SAL annotations Update comments.
### Description <!-- Describe your changes. --> Supports creating a model programmatically using the ORT C or C++ API. Supports augmenting an existing model to add nodes. ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. -->
Description
Supports creating a model programmatically using the ORT C or C++ API.
Supports augmenting an existing model to add nodes.
Motivation and Context