Question about the implementation of decoding
|
|
3
|
1419
|
July 30, 2018
|
How to improve the accuracy of model?
|
|
1
|
1747
|
July 23, 2018
|
New `hook` mechanism
|
|
15
|
3080
|
July 16, 2018
|
Typo on master?
|
|
0
|
702
|
July 5, 2018
|
What's "OpenNMT-py/onmt/modules/Gate.py"?
|
|
0
|
630
|
July 5, 2018
|
Why Lua/Torch? (Please don't hate me for this question.)
|
|
8
|
11545
|
June 4, 2018
|
What's the use of `coverage` in the forward pass for GlobalAttention?
|
|
0
|
858
|
May 31, 2018
|
Could I submit pull request to tokenization hook for Korean and Japanese?
|
|
3
|
1021
|
May 23, 2018
|
Why exclude last target from inputs?
|
|
1
|
1204
|
May 22, 2018
|
OpenNMT-py Using Multiple Encoders
|
|
1
|
1626
|
April 14, 2018
|
Approach to translate one sentence at a time by write one sentence into temp file
|
|
2
|
1558
|
April 13, 2018
|
HDFS support in OpenNMT-tf
|
|
1
|
923
|
April 13, 2018
|
Windows + CUDA working with PyTorch!
|
|
1
|
4005
|
April 6, 2018
|
Choosing number of epochs for a stacked encoder decoder model
|
|
4
|
2274
|
February 13, 2018
|
How computing loss in shards helps reduce memory cost?
|
|
0
|
1210
|
January 13, 2018
|
SentencePiece vs. BPE
|
|
0
|
5135
|
December 7, 2017
|
Custom Loss Function Criterion
|
|
4
|
4647
|
December 20, 2017
|
How to ensemble some models by OpenNMT(pytorch)?
|
|
1
|
1705
|
November 29, 2017
|
How should I choose parameters?
|
|
1
|
1219
|
November 27, 2017
|
Corpus level TER averaging
|
|
2
|
1351
|
November 8, 2017
|
How ensemble decoding
|
|
3
|
2591
|
November 3, 2017
|
OpenNMT : lua code debug
|
|
1
|
1058
|
October 24, 2017
|
Need help understanding copy_attn_force
|
|
2
|
1503
|
October 21, 2017
|
BPE options handling in learn_bpe.lua and tokenizer.lua
|
|
3
|
1547
|
October 19, 2017
|
OpenNMT tagger (CUDA -> CPU) release model
|
|
2
|
1438
|
October 16, 2017
|
Changing the behaviour of `end_epoch` options when used in combination with `train_from` and `continue` options
|
|
4
|
1024
|
October 16, 2017
|
Word features with idx_files
|
|
1
|
1016
|
October 16, 2017
|
Attention only models
|
|
1
|
1116
|
September 25, 2017
|
[Code Understanding] Where are different models 'used' in the source?
|
|
5
|
1508
|
September 23, 2017
|
Can dispatching batches with different src_len degrade performance in synchronous training
|
|
4
|
1097
|
August 22, 2017
|