-
I am able to train a g2p model by g2p-seq2seq, but the problem is this model can't be used by pocket sphinx. If tried it always ends with error "RuntimeError: new_Decoder returned -1".
On the other…
-
[flake8](http://flake8.pycqa.org) testing of https://github.com/tensorflow/tensor2tensor on Python 3.7.0
$ __flake8 . --count --select=E901,E999,F821,F822,F823 --show-source --statistics__
```
./…
-
The bias in `nn.Linear` is enabled by default, and according to [Sockeye](https://github.com/awslabs/sockeye/blob/master/sockeye/layers.py), seems bias in [MultiHeadAttention](https://github.com/OpenN…
-
### Description
hi,guys,
Did someone try universal transformer in machine translation tasks?
My experiments with default settings does not surpass transformer in zh-en mt task.
-
I would enjoy to experiment with an option that would do the following:
- randomize the network, especially the word vector layers.
- train the network WITHOUT updating the word vector layers.
Wo…
-
File "C:\anaconda3\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run
_sys.exit(main(argv))
File "c:/anaconda3/scripts/t2t-datagen", line 23, in main
t2t_datagen.main…
-
I have trained nmt models, but I can not understand how to export the models to tensorflow serving. I read the documentations of **MNIST** and **Inception**, but I think these models are different wit…
-
I am having a hard time extracting the code from tensor2tensor.
-
### Description
Trying to train translate_ende_wmt32k demo with ml-engine, got tensorflow version mismatch error.
looks like t2t 1.11 introduced [tensorflow_probability](https://github.com/tens…
-
How do I fix this?
(magenta) usuario@Strix:~/Escritorio/train$ t2t_decoder --decode_hparams="${DECODE_HPARAMS}" --decode_interactive --hparams="sampling_method=random" --hparams_set=${HPARA…