|
Interpreting the gradients global norm in Tensorboard
|
|
3
|
2403
|
March 18, 2021
|
|
Bad translation results after 30 epochs
|
|
5
|
1959
|
February 7, 2019
|
|
Low bleu score with Sentencepiece comparing to othoner tokenizers
|
|
2
|
2770
|
August 12, 2022
|
|
Large Memory Layers with Product Keys
|
|
3
|
2396
|
October 30, 2019
|
|
Lexical constraints at translation request time?
|
|
3
|
2394
|
November 20, 2017
|
|
BPE question concerning choice of models
|
|
4
|
2140
|
August 5, 2017
|
|
What is the importance of validation files? Can you train without them?
|
|
2
|
2761
|
April 10, 2017
|
|
How do I use Crayon?
|
|
2
|
2758
|
August 11, 2017
|
|
The warning of nccl
|
|
2
|
2758
|
May 17, 2017
|
|
How to add extra information to the Transformer
|
|
3
|
2384
|
July 12, 2021
|
|
Translation example from OpenNMT documentation
|
|
3
|
2379
|
September 14, 2021
|
|
Guided Alignment Training
|
|
8
|
1579
|
March 9, 2021
|
|
Increasing effective batch size
|
|
4
|
2117
|
July 21, 2023
|
|
How to run the translation server on the Docker Image
|
|
2
|
2730
|
March 11, 2019
|
|
<unk> after sentencepiece tokenization
|
|
1
|
3341
|
January 2, 2021
|
|
Converging the training in meaningful time
|
|
4
|
2112
|
September 11, 2017
|
|
Sequence to sequence model not making any attempt to translate with OpenNMT-py
|
|
5
|
1926
|
February 17, 2021
|
|
Translate.py error: 'NoneType' object has no attribute 'transpose'
|
|
1
|
3332
|
March 3, 2017
|
|
Train the onmt with multiple sources on tensorflow v2.0
|
|
3
|
2353
|
March 18, 2020
|
|
Arabic-English Translation with Limited Training Data
|
|
3
|
2351
|
July 21, 2020
|
|
Big Transformer model parameters
|
|
1
|
3323
|
August 6, 2019
|
|
Unified decoding does not support TensorFlow 1.4
|
|
7
|
1661
|
November 17, 2019
|
|
Learning rate not decaying when perplexity stops decreasing on validation set
|
|
5
|
1914
|
February 4, 2019
|
|
Add user data to checkpoint?
|
|
4
|
2095
|
June 8, 2018
|
|
Training steps & continue training explanation?
|
|
1
|
3306
|
May 23, 2019
|
|
Question about the implementation of decoding
|
|
3
|
2337
|
July 30, 2018
|
|
Error while running command train.py
|
|
2
|
2696
|
May 31, 2018
|
|
English to Finnish Translation
|
|
6
|
1763
|
May 24, 2019
|
|
Qs about NMT learning
|
|
7
|
1646
|
March 6, 2020
|
|
Did someone test RNN with larger recurrence?
|
|
5
|
1898
|
June 23, 2017
|
|
Error during train the model
|
|
2
|
2680
|
April 1, 2019
|
|
Core dump while loading the tokenizer
|
|
3
|
2323
|
September 16, 2019
|
|
Which Machine configuration works best for Machine Translation using OpenNMT?
|
|
3
|
2321
|
September 7, 2017
|
|
Quality estimation / pred_score
|
|
3
|
2319
|
October 25, 2017
|
|
TypeError: __init__() got an unexpected keyword argument 'reduction', when using pre-trained embeddings on OpenNMT-py
|
|
1
|
3277
|
October 5, 2018
|
|
Missing 'data/demo.vocab.pt'
|
|
4
|
2070
|
June 5, 2019
|
|
OpenNMT-py experiment results fluctuation
|
|
8
|
1542
|
March 4, 2021
|
|
Quantization Kernels in lower precision
|
|
1
|
3260
|
April 23, 2025
|
|
Ctranslate2 Python Translation API
|
|
4
|
2057
|
July 8, 2022
|
|
AttributeError: 'TransformerDecoder' object has no attribute 'self_attn'
|
|
2
|
2656
|
March 13, 2019
|
|
Fine-tuning failed when loading checkpoint
|
|
3
|
2297
|
February 10, 2020
|
|
Has anyone trained transformer on the multi30k dataset?
|
|
3
|
2295
|
November 9, 2020
|
|
How to speed up when preprocess the corpus ?
|
|
3
|
2293
|
September 28, 2018
|
|
Crash in WordEmbedding.lua
|
|
5
|
1865
|
March 8, 2017
|
|
Freezing layers: how to obtain the names of the layers to freeze?
|
|
3
|
2279
|
February 3, 2020
|
|
The WMT14 English-French result on the Opennmt-py
|
|
3
|
2279
|
May 16, 2017
|
|
Translate_batch discrepancy
|
|
3
|
2271
|
September 24, 2020
|
|
"Train from" - choosing preprocess chunk
|
|
3
|
2270
|
July 20, 2020
|
|
How to remove unwanted words like 's or "
|
|
3
|
2260
|
July 17, 2020
|
|
A version-related torchtext question on _dynamic_dict function
|
|
1
|
3195
|
March 22, 2022
|