|
Seq_length and vocab_size no change
|
|
2
|
2058
|
February 14, 2021
|
|
Pre trained models for transfer learning?
|
|
2
|
2054
|
February 13, 2018
|
|
Quantization Kernels in lower precision
|
|
1
|
2513
|
April 23, 2025
|
|
How Much Does Tokenization Affect Neural Machine Translation?
|
|
1
|
2516
|
June 21, 2021
|
|
How to limit GPU usage?
|
|
4
|
1586
|
August 2, 2018
|
|
Examples of classification / regression using API
|
|
1
|
2504
|
January 24, 2017
|
|
Install torch on MacOS [SOLVED]
|
|
2
|
2041
|
October 9, 2018
|
|
Size of 'h' is zero during beam search (in Beam.lua)
|
|
4
|
1578
|
March 15, 2017
|
|
Server running in one terminal but curl return empty response
|
|
1
|
2496
|
March 12, 2019
|
|
-train_from and train_from_state_dict
|
|
3
|
1764
|
June 30, 2017
|
|
Dynamic dictionary in the preprocessing step
|
|
4
|
1577
|
October 28, 2019
|
|
How to auto detect the source language using the OpenNMT Server
|
|
3
|
1759
|
March 19, 2019
|
|
Difficulty in translating easy sentences
|
|
5
|
1434
|
July 17, 2019
|
|
Retraining fails from pretrained models
|
|
2
|
2024
|
July 24, 2018
|
|
Source/target tokenization/de-tokenization with SentencePiece
|
|
2
|
2020
|
March 20, 2019
|
|
Save trained models per iteration
|
|
5
|
1428
|
October 23, 2018
|
|
How to extract the word embedding vector from a trained model?
|
|
2
|
2016
|
December 14, 2017
|
|
Core dump while running server.py
|
|
2
|
2015
|
August 16, 2019
|
|
OpenNMT for SpellCheck
|
|
1
|
1385
|
February 28, 2024
|
|
IndexError when training
|
|
3
|
1740
|
March 28, 2019
|
|
OpenNMT-tf MixedInputter (BERT embedding + character embedding)
|
|
3
|
1739
|
October 29, 2021
|
|
How to use GPU while training?
|
|
2
|
2009
|
August 22, 2019
|
|
OpenNMT tagger (CUDA -> CPU) release model
|
|
2
|
2006
|
October 16, 2017
|
|
Saving embedding weights from LM
|
|
3
|
1737
|
March 15, 2021
|
|
Differences between different NMT frameworks
|
|
1
|
2452
|
March 6, 2017
|
|
The Ultimate wish-list for OpenNMT-Lua
|
|
1
|
2446
|
January 30, 2018
|
|
OpeNMT-tf memory error
|
|
7
|
1221
|
May 16, 2022
|
|
Paraphrase generation with OpenNMT
|
|
2
|
1986
|
October 11, 2017
|
|
Multilingual pretrained model: help / weird output
|
|
1
|
2432
|
October 9, 2018
|
|
Ctranslate2 : target_prefix option
|
|
2
|
1983
|
November 9, 2021
|
|
Use a pre-trained Bert model for for sequence classification
|
|
2
|
1983
|
October 13, 2021
|
|
Has anyone trained transformer on the multi30k dataset?
|
|
3
|
1711
|
November 9, 2020
|
|
Has anyone experimented with the dense bridge?
|
|
2
|
1975
|
January 8, 2019
|
|
Evaluation error during training
|
|
4
|
1526
|
December 2, 2021
|
|
Specifying input feed required to use global attention?
|
|
2
|
1968
|
August 30, 2018
|
|
Training on GPU - Cuda Unknown error
|
|
1
|
2403
|
August 23, 2019
|
|
Automating hyperparameter optimization
|
|
1
|
2403
|
March 9, 2018
|
|
Poor BLEU score with WMT Chinese-English translation
|
|
2
|
1960
|
April 5, 2019
|
|
VOTE and certains words are repeated several times in translation
|
|
2
|
1959
|
August 23, 2019
|
|
Attention mechanism without translation
|
|
4
|
1518
|
February 26, 2020
|
|
On-the-fly Tokenization
|
|
4
|
1516
|
August 9, 2021
|
|
Out of memory (OpenNMT 0.3 vs OpenNMT 0.7)
|
|
4
|
1515
|
June 20, 2017
|
|
N-best rescoring feature in Opennmt-py
|
|
6
|
1281
|
July 16, 2019
|
|
Question on some results on the Benchmark platform
|
|
5
|
1377
|
March 20, 2017
|
|
Unable to use GPU
|
|
2
|
1937
|
November 12, 2018
|
|
About Unknown Words
|
|
3
|
1678
|
May 30, 2019
|
|
Opennmt-tf tokenizer using case_feature issue
|
|
5
|
1369
|
June 25, 2020
|
|
Tok_(src|tgt)_case_feature + DynData training, translate <unk> rather than L or N
|
|
5
|
1367
|
October 6, 2017
|
|
Python version not documented
|
|
3
|
1675
|
December 8, 2017
|
|
Using multi-cores on a GPU
|
|
5
|
1366
|
September 14, 2018
|