OpenNMT Forum

Development


Topic Replies Activity
Why exclude last target from inputs? 2 May 22, 2018
OpenNMT-py Using Multiple Encoders 2 April 14, 2018
Approach to translate one sentence at a time by write one sentence into temp file 3 April 13, 2018
HDFS support in OpenNMT-tf 2 April 13, 2018
Windows + CUDA working with PyTorch! 2 April 6, 2018
Choosing number of epochs for a stacked encoder decoder model 5 February 13, 2018
How computing loss in shards helps reduce memory cost? 1 January 13, 2018
SentencePiece vs. BPE 1 December 7, 2017
Custom Loss Function Criterion 5 December 20, 2017
How to ensemble some models by OpenNMT(pytorch)? 2 November 29, 2017
How should I choose parameters? 2 November 27, 2017
Corpus level TER averaging 3 November 8, 2017
How ensemble decoding 4 November 3, 2017
OpenNMT : lua code debug 2 October 24, 2017
Need help understanding copy_attn_force 3 October 21, 2017
BPE options handling in learn_bpe.lua and tokenizer.lua 4 October 19, 2017
OpenNMT tagger (CUDA -> CPU) release model 3 October 16, 2017
Changing the behaviour of `end_epoch` options when used in combination with `train_from` and `continue` options 5 October 16, 2017
Word features with idx_files 2 October 16, 2017
Attention only models 2 September 25, 2017
[Code Understanding] Where are different models 'used' in the source? 6 September 23, 2017
Can dispatching batches with different src_len degrade performance in synchronous training 5 August 22, 2017
OpenCL instead of CUDA 4 August 18, 2017
Gradient checking 3 August 16, 2017
Adaptive Learning in OpenNMT 11 August 4, 2017
How to use multi-GPU parallel training with an old commit on Feb 23 2 July 25, 2017
-train_from and train_from_state_dict 4 June 30, 2017
Add support for distributed training on multiple CPU only nodes 2 June 28, 2017
Can we use language translation model for Hindi to English translation? 2 June 27, 2017
outputs.backward(gradOutput) 7 June 22, 2017