OpenNMT/OpenNMT-tf

Compatibility with Visualization Tool SeqtoSeq Vis /LSTMVis

Open

#478 opened on Aug 6, 2019

View on GitHub
 (6 comments) (0 reactions) (0 assignees)Python (1,428 stars) (394 forks)batch import
help wantedquestion

Description

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 !

Contributor guide

Tech stack
python
Domain
machine learning
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
3-5 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
TensorFlow model formatPyTorch model formatOpenNMT tf architectureModel conversion techniques
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
20
Research direction
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.