-
layers/common_hparams.py mentions a hyperparameter "pretrained_model_dir":
"Directory containing a checkpoint for a pretrained model. This will only be used if a new run is being started. Parameter…
-
### Description
I'm trying to add features to a translation problem, I have a separate file with a line per input line, containing two integers.
I manage to store the values in the tfrecor…
-
I use the transformer encoder code like below to train and dump the model.
```
from tensor2tensor.models import transformer
import tensorflow as tf
hparams = transformer.transformer_base()
enco…
-
Hello!
Is it possible to change inference type for lms from sampling next sentence based on target to calculating perplexity of target sentence as it is without changing too much code?
The way I se…
-
### System information
- **What is the top-level directory of the model you are using**: models
- **Have I written custom code (as opposed to using a stock example script provided in TensorFlow)**:N…
-
### Description
Should Universal Transformer work with TPU? Tried a spin at getting it to work and isn't.
Model + hparams below.
I do see that there are _tpu specific hparam sets for Transfo…
-
> [root@localhost fairseq-zh-en]# ./wmt17_generate.sh
optimizing fconv for decoding
decoding to tmp/wmt17_en_zh/fconv_test
/root/torch/install/bin/luajit: .../install/share/lua/5.1/fairseq/models/e…
-
이번 수업으로 deep-learning을 처음 접하다보니
분산시스템에 알맞는 데이터셋을 고르는데 좀 어려움이 있네요.
혹시 데이터셋을 좀 추천해주실 수 있을까요?
-
I am training a transformer on a summarization task. My results does not seem promising. I think it would be useful to the community if someone has achieved good results on the summarization task (any…
-
Hi guys, congrats and thanks for development and help.
I would like to apply the most modern deep-learning techniques for analysis of sequential data to TIMESERIES coming from physical and chemical…