1. 07 Dec, 2020 1 commit
  2. 02 Nov, 2020 2 commits
  3. 22 Oct, 2020 2 commits
  4. 05 Oct, 2020 1 commit
  5. 01 Oct, 2020 1 commit
  6. 21 Sep, 2020 1 commit
  7. 17 Sep, 2020 1 commit
  8. 08 Sep, 2020 1 commit
  9. 08 Aug, 2020 1 commit
  10. 28 Jul, 2020 1 commit
  11. 10 Jul, 2020 1 commit
  12. 01 Jul, 2020 1 commit
  13. 26 Jun, 2020 1 commit
  14. 24 Jun, 2020 1 commit
  15. 22 Jun, 2020 1 commit
  16. 03 Jun, 2020 1 commit
  17. 02 Jun, 2020 1 commit
  18. 29 May, 2020 2 commits
  19. 28 May, 2020 3 commits
  20. 26 May, 2020 1 commit
  21. 22 May, 2020 2 commits
  22. 20 May, 2020 1 commit
  23. 19 May, 2020 1 commit
  24. 18 May, 2020 1 commit
  25. 14 May, 2020 2 commits
    • Morgan Funtowicz's avatar
      Updated ONNX notebook link in README. · 84894974
      Morgan Funtowicz authored
      84894974
    • Funtowicz Morgan's avatar
      Conversion script to export transformers models to ONNX IR. (#4253) · db0076a9
      Funtowicz Morgan authored
      * Added generic ONNX conversion script for PyTorch model.
      
      * WIP initial TF support.
      
      * TensorFlow/Keras ONNX export working.
      
      * Print framework version info
      
      * Add possibility to check the model is correctly loading on ONNX runtime.
      
      * Remove quantization option.
      
      * Specify ONNX opset version when exporting.
      
      * Formatting.
      
      * Remove unused imports.
      
      * Make functions more generally reusable from other part of the code.
      
      * isort happy.
      
      * flake happy
      
      * Export only feature-extraction for now
      
      * Correctly check inputs order / filter before export.
      
      * Removed task variable
      
      * Fix invalid args call in load_graph_from_args.
      
      * Fix invalid args call in convert.
      
      * Fix invalid args call in infer_shapes.
      
      * Raise exception and catch in caller function instead of exit.
      
      * Add 04-onnx-export.ipynb notebook
      
      * More WIP on the notebook
      
      * Remove unused imports
      
      * Simplify & remove unused constants.
      
      * Export with constant_folding in PyTorch
      
      * Let's try to put function args in the right order this time ...
      
      * Disable external_data_format temporary
      
      * ONNX notebook draft ready.
      
      * Updated notebooks charts + wording
      
      * Correct error while exporting last chart in notebook.
      
      * Adressing @LysandreJik comment.
      
      * Set ONNX opset to 11 as default value.
      
      * Set opset param mandatory
      
      * Added ONNX export unittests
      
      * Quality.
      
      * flake8 happy
      
      * Add keras2onnx dependency on extras["tf"]
      
      * Pin keras2onnx on github master to v1.6.5
      
      * Second attempt.
      
      * Third attempt.
      
      * Use the right repo URL this time ...
      
      * Do the same for onnxconverter-common
      
      * Added keras2onnx and onnxconveter-common to 1.7.0 to supports TF2.2
      
      * Correct commit hash.
      
      * Addressing PR review: Optimization are enabled by default.
      
      * Addressing PR review: small changes in the notebook
      
      * setup.py comment about keras2onnx versioning.
      db0076a9
  26. 06 Apr, 2020 1 commit
  27. 19 Mar, 2020 1 commit
  28. 18 Mar, 2020 1 commit
  29. 05 Mar, 2020 2 commits
  30. 04 Mar, 2020 3 commits