|
Reduction in size of checkpoints: `--train_from` arg
|
|
1
|
13
|
August 10, 2020
|
|
Lesser BLEU score compared to Fairseq
|
|
5
|
65
|
July 31, 2020
|
|
ONMT multiprocess inference on CPU in production
|
|
4
|
102
|
July 10, 2020
|
|
Fast CPU decoding
|
|
4
|
1310
|
October 11, 2019
|
|
Linguistic features surprisingly decrease the performance!
|
|
20
|
2547
|
May 14, 2019
|
|
Does converting trained model from FP32 to FP16 improve inference performance?
|
|
3
|
626
|
April 30, 2019
|
|
Multi-GPUs is slower than single GPU
|
|
13
|
2763
|
April 16, 2019
|
|
Advice on new GPU
|
|
11
|
922
|
January 1, 2019
|
|
Translating huge number of sentences
|
|
3
|
388
|
December 12, 2018
|
|
What is the relationship between ppl, accuracy and bleu scores in machine translation? In my experiment, although ppl and accuracy on the validationset are greatly improved, Bleu scores is reduced
|
|
1
|
906
|
November 25, 2018
|
|
Is the speed of CTranslate faster than that of lua version?
|
|
14
|
2186
|
June 18, 2018
|
|
Why Lua/Torch? (Please don't hate me for this question.)
|
|
9
|
7083
|
June 4, 2018
|
|
Training Speed on AWS p2.xlarge
|
|
2
|
773
|
February 22, 2018
|
|
Choosing number of epochs for a stacked encoder decoder model
|
|
5
|
1373
|
February 13, 2018
|
|
BLEU very low with the almost baseline model NMT
|
|
2
|
645
|
February 6, 2018
|
|
Raising training speed without comprimising too much on quality
|
|
8
|
807
|
December 4, 2017
|
|
Which Machine configuration works best for Machine Translation using OpenNMT?
|
|
4
|
1008
|
September 7, 2017
|
|
Torch vs pyTorch
|
|
3
|
1103
|
July 20, 2017
|
|
Add support for distributed training on multiple CPU only nodes
|
|
2
|
1043
|
June 28, 2017
|
|
Mini batch size
|
|
4
|
2546
|
May 5, 2017
|
|
How to speed up beam search?
|
|
6
|
1836
|
March 8, 2017
|
|
Comparing OpenNMT and PyOpenNMT efficiency
|
|
1
|
1530
|
February 24, 2017
|
|
Performance analysis number
|
|
2
|
1089
|
January 26, 2017
|