|
Bad results from DE-EN Pretrained models
|
|
11
|
4227
|
January 2, 2019
|
|
How to load pretrained word2vec embedding files with opennmt-tf?
|
|
1
|
2173
|
January 2, 2019
|
|
Advice on new GPU
|
|
10
|
3142
|
January 1, 2019
|
|
Transformer model error
|
|
1
|
1725
|
December 24, 2018
|
|
BLEU was OK at the beginning, but decreased to 0
|
|
5
|
2012
|
December 21, 2018
|
|
How to specify input data files for ParallelInputter?
|
|
2
|
1417
|
December 18, 2018
|
|
Restoring of source formatting
|
|
13
|
4551
|
December 18, 2018
|
|
Cuda OOM for Validation
|
|
8
|
2075
|
December 17, 2018
|
|
Early stopping parameters for default transformer config?
|
|
2
|
1892
|
December 14, 2018
|
|
Large perplexity
|
|
6
|
2547
|
December 12, 2018
|
|
Translating huge number of sentences
|
|
2
|
1981
|
December 12, 2018
|
|
Question about using the Pretrained embedding
|
|
3
|
2440
|
December 10, 2018
|
|
"Import pyonmttok" failed & "pip install pyonmttok" faileld - Windows 10
|
|
1
|
3062
|
December 8, 2018
|
|
OpenNMT-tf Fine tuning base model gives worse and decreases BLEU scores
|
|
8
|
2218
|
December 5, 2018
|
|
Handle numbers, urls, dates
|
|
2
|
2777
|
December 5, 2018
|
|
TransformerBig model - GTX 1080 Ti (11G) - ResourceExhaustedError
|
|
8
|
3703
|
December 5, 2018
|
|
Use GloVe with concatenated word features (OpenNMT-py)
|
|
0
|
1351
|
December 5, 2018
|
|
Tokenization OpenNMT-tf
|
|
3
|
1380
|
December 4, 2018
|
|
Using multiple gpus in training.py
|
|
4
|
3577
|
December 1, 2018
|
|
Translation server in OpenNMT-tf
|
|
2
|
1499
|
November 30, 2018
|
|
Perplexity in opennmt-tf
|
|
1
|
1606
|
November 30, 2018
|
|
Alignment not coming properly
|
|
1
|
1423
|
November 30, 2018
|
|
OpenNMT-tf Distributed Training - Processes don't end after training completes
|
|
4
|
1602
|
November 29, 2018
|
|
OpenNMT-tf serving with latest prediction_service_pb2_grpc for translation
|
|
2
|
2979
|
November 28, 2018
|
|
Hi , I have 130k train src tgt pairs, but the log info of training process shows that there are only 22k train pairs after we preprocess the data
|
|
4
|
1517
|
November 25, 2018
|
|
Issues when running the English-German WMT15 training
|
|
22
|
6844
|
November 22, 2018
|
|
Issue in using distributed training in openNMT-TF
|
|
31
|
4950
|
November 21, 2018
|
|
Beam Search with target words features: how does it work?
|
|
3
|
1401
|
November 21, 2018
|
|
Generating learning curves using OpenNMT-py version
|
|
2
|
1674
|
November 21, 2018
|
|
Opnenmt-th takes so long to load training data before it really starts the training process
|
|
2
|
1326
|
November 21, 2018
|