-
## 一言で言うと
アテンション付きseq2seqの目的関数をいろいろ比較してみました。
### 論文リンク
[Classical Structured Prediction Losses for Sequence to Sequence Learning](http://aclweb.org/anthology/N18-1033)
### 著者/所属機関
Sergey Edun…
-
Hi, here's a list of questions I have. None of them warrant a separate issue, but clarifying those would help new users such as myself
- [x] How do I force the overwrite of the log file? The error …
-
We've created a higher level API for recurrent neural networks and have completed gradient tests, forward test and speed comparison against CuDNN. The class definition and key methods look like this:…
-
I am using a machine with 16 GPUs.
But with the training. they write "training on 1 GPUs"
```
[de] dictionary: 10433 types
[en] dictionary: 10389 types …
-
I was following your annotated Ipython code, and some weird error came up during data loading section.
```
.data/iwslt/de-en/IWSLT16.TED.tst2012.de-en.en.xml
-----------------------------------…
KyonP updated
6 years ago
-
OS: Linux version 2.6.32-696.6.3.el6.x86_64 (Red Hat 4.4.7-18)
CUDA : 9.1
CUDNN : 8.0
I have compile pytorch and fairseq successfully on my machine, and also executed preprocess command with…
-
I followed the readme to start train the model.But the problem is always here.
Does anyone else have the same question? How do you fix it.
CUDA_VISIBLE_DEVICES=3 python train.py data-bin/iwslt14.t…
-
Can you please tell which preprocessing did you use? I found that original IWSLT consist of some xml files. Thank you!
-
Hi all,
We will be at the Machine Translation Marathon in Prague. Do you guys have ideas or demands for a fun project to propose?
-
I am trying to run the LSTM model. The command is `CUDA_VISIBLE_DEVICES=0 python train.py data-bin/iwslt14.tokenized.de-en --optim adam --lr 0.0003125 --clip-norm 0.1 --dropout 0.2 --max-tokens 4000 -…