Comments (4)
a good example to start with is here: https://github.com/EdinburghNLP/wmt17-transformer-scripts/tree/master/training
--valid_script
is used to define the external evaluation script. Note that the interface is slightly different from the theano version: the validation script (in the example validate.sh ) will receive a temporary file path as first argument (the file contains the raw translation output), and has to return a score on stdout.
from nematus.
thanks. Actually, I am trying to map quite old nematus option setting to the current nematus with tensorflow.
Could you help me check it? For example, dropout_embedding seems removed instead of rnn_dropout_embedding or transformer_dropout_embedding. For validFreq and so on, I know they become valid_freq..
python ../nematus/train.py
--model models/model.$TRAINSIZE.$MSGVSIZE.$DIFFVSIZE.npz
--dim_word 512
--dim 1024
--n_words_src $DIFFVSIZE
--n_words $MSGVSIZE
--decay_c 0
--clip_c 1
--lrate 0.0001
--optimizer adam
--maxlen 400
--batch_size 80
--valid_batch_size 80
--datasets data/train.$TRAINSIZE.diff data/train.$TRAINSIZE.msg
--valid_datasets data/valid.$VALIDSIZE.diff data/valid.$VALIDSIZE.msg
--dictionaries data/vocab.diff.$DIFFVSIZE.json data/vocab.msg.$MSGVSIZE.json
--validFreq 10000
--dispFreq 1000
--saveFreq 30000
--sampleFreq 10000
--dropout_embedding 0.2
--dropout_hidden 0.2
--dropout_source 0.1
--dropout_target 0.1
--no_shuffle
--valid_script "validate.sh"
from nematus.
from nematus.
thanks a lot. and for translate.py -p option has been removed.
from nematus.
Related Issues (20)
- Docker: No module named 'rescore' HOT 1
- Throws error when running with rnn_dropout_embedding: true parameter HOT 5
- Load model from Opus-MT HOT 6
- 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.