Comments (6)
Hi, marian-nmt maintainer here. That assumption hasn't been true for a while. Only a certain class of RNN-based used to compatible with old Theano-based Nematus. Not sure if that is still the case.
from nematus.
Hi, thanks for the quick feedback :)
The pretrained models seem to be in a very readable format. It's lots of .npy files.
Is there some documentation on the layout? Can I manually reproduce the corresponding model in tensorflow and read in the weights?
I would love to use marian-nmt or opus-mt but for deployment, it has to be tensorflow.
from nematus.
The Hugging face people are cooking something up right now. So maybe just wait? I am sure they will announce it.
from nematus.
If you can't wait, or just for those interested: if multiple toolkits implement the same, well-defined architecture (like the Transformer), it's possible in principle to map the parameters from one to the other. We also wrote such a conversion to port RNN models from our Theano to our Tensorflow codebase: https://github.com/EdinburghNLP/nematus/blob/master/nematus/theano_tf_convert.py
However, the devil is in the details. For example, implementations may have slight differences in the architecture (some well-known variants are pre-norm and post-norm Transformers, see https://arxiv.org/pdf/1906.01787.pdf ), and if the architecture differs, you will not be able to port models between toolkits by just copying the weights.
from nematus.
If it was only architecture that would be easy :) E.g. between Marian and Fairseq one of the differences is a positional embedding starting point shifted by 1. Try to find that by yourself.
Then again it's an opportunity to learn all the things you never want to know about not one but two toolkits! :)
from nematus.
Something potentially working. All questions to be directed to the Huggingface people :)
from nematus.
Related Issues (20)
- Docker: No module named 'rescore' HOT 1
- Throws error when running with rnn_dropout_embedding: true parameter HOT 5
- how to map --external_validation_script option to the current nematus with tensorflow? HOT 4
- reimplement rnn of nematus
- How to continue training from the last checkpoint HOT 5
- Why use tie_encoder_decoder_embeddings instead of tie_decoder_embeddings in line 131 of transformer.py? HOT 3
- question about the self-attention in the Encoder HOT 2
- decoding in the Transformer-based model HOT 12
- Training stops after few epochs HOT 1
- beam search HOT 1
- translation_maxlen HOT 2
- Performance issues in the difinition of generate_initial_memories, nematus/transformer_inference.py HOT 1
- OP_REQUIRES failed at strided_slice_op.cc:108 : Invalid argument: slice index -1 of dimension 1 out of bounds. HOT 2
- Config mrt_ml_mix seems to be unused HOT 1
- TensorArray Not Used on line 240 of mrt_utils.py
- multiple models (with same vocabulary) for ensemble decoding HOT 2
- None exception HOT 4
- Question about running on GPU HOT 3
- A request for system version updates HOT 5
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from nematus.