OpenNMT Forum

Topic Replies Activity
Sentencepiece decoding 18 May 14, 2019
Linguistic features surprisingly decrease the performance! 20 May 14, 2019
Training loss vs Eval loss 5 May 14, 2019
The difference between maximum_labels_length and maximum_iterations 2 May 14, 2019
Retrain a model with fixed emebeddings 9 May 13, 2019
Fixed vs trainable embeddings 6 May 13, 2019
Reset learning rate after update-vocabulary 3 May 13, 2019
Transformer: Freezing Encoder while training Decoder 3 May 13, 2019
Transformer model on 2 GPU vs. 4 GPU 5 May 11, 2019
Comparing transformer model in OpenNMT-py vs OpenNMT-tf 9 May 9, 2019
Question about the performance between one GPU and two GPUs 3 May 9, 2019
Phrase-based translation in OpenNMT-py 2 May 9, 2019
Inferring Big File 2 May 9, 2019
The min ppl is about 4.5; should I continune the training? 2 May 9, 2019
Do OpenNMT support machine transliteration? 4 May 9, 2019
Source and target word correspondence in Opennmt-py 3 May 7, 2019
Tokenization, emedding and transformer with OpenNMT-py 5 May 7, 2019
Train Transformer model on Google Colab 2 May 6, 2019
CUDA out of memory in validation step 4 May 6, 2019
Cannot translate some sentences 9 May 6, 2019
Arabic to English translation model 3 May 5, 2019
Question about the relationship between train_steps and epochs 3 May 3, 2019
Load checkpoint and compute Transformer encoder output failure 3 May 3, 2019
Why the gpu use ratio is low? 4 May 3, 2019
Does converting trained model from FP32 to FP16 improve inference performance? 3 April 30, 2019
Parameters tuning for translation Italian - English 3 April 29, 2019
Error in training using embeddings 1 April 29, 2019
Decoding with LM 2 April 28, 2019
Training a baseline pointer generator model with OpenNMT 2 April 28, 2019
Language Model scorer and sampler 20 April 28, 2019