OpenNMT/OpenNMT-tf

Compatibility with Visualization Tool SeqtoSeq Vis /LSTMVis

Open

#478 建立於 2019年8月6日

在 GitHub 查看
 (6 留言) (0 反應) (0 負責人)Python (1,428 star) (394 fork)batch import
help wantedquestion

描述

Hi,

I came across this Vis tool (Seq2seq vis or lstm vis) effectively shows some good visualizations for Sequence models. Looks like it uses model files form the other repo OpenNMT-py. Is there any way I can use this with the model files that are generated from this repo or out of box conversion to pyTorch models ? Otherwise I'm guessing I have to run the same experiments again with OpenNMT-py.

Thanks !

貢獻者指南

技術棧
python
領域
machine learning
議題類型
feature
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
3
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
3-5 days
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
stale
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
mostly clear
前置要求
TensorFlow model formatPyTorch model formatOpenNMT tf architectureModel conversion techniques
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
20
研究方向
Investigate if there are any existing utilities in OpenNMT tf for exporting models to a format compatible with PyTorch based visualization tools. Check the repository's documentation and model export functions. If not, consider implementing a conversion script that maps TensorFlow model weights to PyTorch state dict. Also review the comments in issue #478 for any progress or suggestions from the community.