Skip to content

GitLab

Switch branch/tag
  1. 18 May, 2020 2 commits
  3. 15 May, 2020 1 commit
  5. 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
  7. 13 May, 2020 1 commit
  9. 28 Apr, 2020 1 commit
  11. 16 Apr, 2020 1 commit
  13. 10 Apr, 2020 1 commit
  15. 06 Apr, 2020 1 commit
  17. 27 Mar, 2020 1 commit
  19. 19 Mar, 2020 2 commits
    • Kyeongpil Kang's avatar
      Update 01-training-tokenizers.ipynb (typo issue) (#3343) · 8eeefcb5
      Kyeongpil Kang authored 
      I found there are two grammar errors or typo issues in the explanation of the encoding properties.

The original sentences:
If your was made of multiple \"parts\" such as (question, context), then this would be a vector with for each token the segment it belongs to
If your has been truncated into multiple subparts because of a length limit (for BERT for example the sequence length is limited to 512), this will contain all the remaining overflowing parts.

I think "input" should be inserted after the phrase "If your".
      8eeefcb5
    • Kyeongpil Kang's avatar
      Fix wrong link for the notebook file (#3344) · 3bedfd33
      Kyeongpil Kang authored 
      For the tutorial of "How to generate text", the URL link was wrong (it was linked to the tutorial of "How to train a language model").

I fixed the URL.
      3bedfd33
  21. 18 Mar, 2020 2 commits
  23. 08 Mar, 2020 1 commit
  25. 05 Mar, 2020 4 commits
  27. 04 Mar, 2020 3 commits
  29. 06 Jan, 2020 2 commits
  31. 05 Jul, 2019 1 commit
  33. 03 Jul, 2019 1 commit
  35. 24 Jun, 2019 1 commit
  37. 20 Jun, 2019 1 commit
  39. 26 Nov, 2018 1 commit
  41. 17 Nov, 2018 1 commit
  43. 16 Nov, 2018 2 commits
  45. 15 Nov, 2018 1 commit
  47. 06 Nov, 2018 1 commit
  49. 05 Nov, 2018 2 commits