High Rank RNN model as Encoder or Decoder [Research] (2)
Server always returning empty list [Support] (7)
Setting up Back-translation in OpenNMT script [Development] (1)
OpenNMT-tf replace_unknown_target does not work [Support] (8)
How to know the case of UNK? [Support] (1)
Inferences from non-training data all giving the same result in OpenNMT-tf [Support] (3)
How can use -start_epoch in OpenNMT-py? [Support] (3)
OpenNMT-tf : Error serving model trained with tensorflow-gpu in tensorflow without gpu [Support] (8)
Using multi-cores on a GPU [Support] (6)
Cannot find any OpenNMT AMI on EC2 [Support] (5)
How long should the training with the default data take? [Support] (8)
Incorporating translation dictionary during decoding [Support] (11)
Is there any method to force loading the full dataset into memroy instead of lazily load in OpenNMT-py? [Support] (1)
Simple OpenNMT-py REST server [Tutorials] (3)
Terminology handling [Feature Requests] (12)
-phrase_table option ( 2 ) [Support] (30)
Training multiple shards not working for the pytorch version? [Support] (3)
Opts.py files for the published papers [Research] (3)
How to change encoder and decoder initial states? [Development] (1)
Beam Search Global Scorer [Research] (1)
Combining BPE and sequence tagging [Research] (1)
Two short questions on training [Support] (2)
English-Marathi and Hindi Translator [Development] (1)
Where to define other plots for tensorboard? [Support] (2)
About "A Deep Reinforced Model for Abstractive Summarization" [Research] (3)
Preprocess with -dynamic_dict does not create a valid data file? [Support] (2)
Horrible results with beam width and replace_unk [Support] (5)
Problem with incremental/in-domain training ( 2 ) [Support] (35)
Multi way training [Support] (4)
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 [Support] (4)