mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-17 21:10:43 +00:00
**Description**: As title. **Motivation and Context** - PyTorch ONNX exporter heavily depends on ONNX shape inference to export accurate and efficient model. Custom symbolic function exports the op as contrib ops, thus exporter is unable to perform standard onnx shape inference. Models with dynamic shape inputs are affected. |
||
|---|---|---|
| .. | ||
| util | ||
| __init__.py | ||
| convert_onnx_models_to_ort.py | ||
| create_reduced_build_config.py | ||
| dump_ort_model.py | ||
| dump_subgraphs.py | ||
| example_operator_perf_test.py | ||
| FindOptimizerOpsetVersionUpdatesRequired.py | ||
| gen_contrib_doc.py | ||
| gen_opkernel_doc.py | ||
| gen_ort_mobile_pkg_doc.py | ||
| get_submodules.py | ||
| onnx_test_data_utils.py | ||
| ort_test_dir_utils.py | ||
| PythonTools.md | ||
| register_custom_ops_pytorch_exporter.py | ||
| remove_initializer_from_input.py | ||
| run_android_emulator.py | ||
| sparsify_initializers.py | ||
| update_version.py | ||