-
Guys,
I got a simple question.
On Table 2., you report 29.3 for the EN-DE Bleu, comparing with Vaswani's original paper 28.4
Unless I am mistaken, all scores reported by the original paper are deto…
-
Hi team!
I'm testing the performance of the new **Tranformer** model on a translation task English to Italian. I created my own data-generator task and problem. I trained an engine on a single GPU …
-
### Description
I would like to know how to export the tensor2tensor serving as a .pb file, rather than a .pbtxt file.
Alternately, how can I get the output node names from the checkpoints/.pbtxt …
-
### Description
Pypi tensor2tensor doesn't work atm
### Environment information
```
OS: OSX
```
Command
```
etragas$ pip install tensor2tensor --force-reinstall
```
Output:
```
Collect…
-
Hi guys,
In en-de and en-fr transformer-big examples, adam_betas is set to (0.9, 0.98), which is the setting used in the Vaswani et al. 2017 paper.
However, in the latest tensor2tensor repo, Adam …
-
v1.4.0 dropped support for multi-task training. This is a tracking issue to discuss how we may be able to add that support back.
Initial thinking is to have a `MultiProblem` subclass of `Problem` …
-
Hello,
I am trying to train a custom Transformer model that has a decoder only (with a custom bottom['targets']), for sequence generation. I was able to train and generate from the model when I had…
-
Hi,
I want to use tensor2tensor to build a Language model for another language based on over 1M sentences I have.
I couldn't find any example for what is the best way to do so - is it possible? How?
okoub updated
5 years ago
-
I am running the following script (from the README.md example) which is supposed to train a `Transformer` model on the `librispeech_clean_small` `Problem`.
The problem I see is that after printing
…
-
I try to set it with `tf.flags.FLAGS.DEFINE_float("worker_gpu_memory_fraction", 0.5, "")` according to the source code https://github.com/tensorflow/tensor2tensor/blob/master/tensor2tensor/bin/t2t_tra…