-
My commands...
PROBLEM=e2_e_nlg
MODEL=transformer
HPARAMS=transformer_base_single_gpu
DATA_DIR=./t2t_data
TMP_DIR=./tmp/t2t_datagen
TRAIN_DIR=./t2t_train/$PROBLEM/$MODEL-$HPARAMS
mkdir …
-
### Description
Installation of tensor2tensor 1.13.01 comes with the installation of tensorflow2.3
Conflicts with tensorflow GPU 1.13.1. GPU cannot be used
How to solve it
### Environment info…
-
Is it possible to achieve the same result as the paper in short time?
Well.. I don't have enough GPU & computation power to see the enough result as google ai.
If we can't train the full corpus as…
-
I add a recurrent layer to the model body, as in my model the current output depends on the previous. It runs well in single GPU but fails when use multi-gpu. the log looks as below:
```
INFO:tensor…
-
### Description
So I am running tensor2tensor framework with my own model, and I see that --train_steps flag not working., it keeps on training past 1000 that I have defined and stops above 200000 (s…
-
### Description
I created a multiprocess_generate supporting problem, using ChoppedTextProblem as a template.
When I actually run the generation, it eventually froze. I used [Pyrasite](http://py…
-
From the paper, the position embedding formula is
```
PE(pos, 2i) =sin(pos / 10000 ** 2i / dmodel)
PE(pos, 2i+1) =cos(pos / 10000 ** 2i / dmodel)
```
So the odd index values are computed by cos,…
-
### Description
Using Google Cloud Storage for `--data_dir` fails. Using gs paths like `gs://my-bucket/path/to/folder` fails.
**NOTE**: This is most likely a Tensorflow bug than Tensor2Tensor bu…
-
**Describe the feature and the current behavior/state.**
I am new to deep learning and tensorflow and recently I created a model similar to the [transformer model](https://www.tensorflow.org/tutorial…
-
### Description
I am unable to install trax using pip in an Ubuntu18.04 VM (windows10 host).
It could not install tensorflow>=2.2 on the default python (3.6.9).
So I installed Python3.8. But the…