-
Hello
I got the errors about jaxlib when I was trying to install tensor2tensor on windows.
The error message was blow
ERROR: Could not find a version that satisfies the requirement jaxlib>=0.1.51…
-
### Description
Successfully trained a model with the provided timeseries toy example problem tensor2tensor/tensor2tensor/data_generators/timeseries.py
after running the t2t-decoder it barked wit…
-
### Description
The `t2t-trainer` command fails to run.
### Environment information
```
Google Colab environment.
In fact, you can just reproduce this problem merely by executing the note…
-
### Description
Batch normalization gets applied here:
https://github.com/tensorflow/tensor2tensor/blob/master/tensor2tensor/layers/common_layers.py#L632
Per https://www.tensorflow.org/versi…
-
This change happened in https://github.com/tensorflow/tensor2tensor/commit/f7695e8d5c9d403fed763c0cc351c6835516e6f3#diff-750434e84a49123af08c4226eb4962f7R399
It seems less than ideal to switch defa…
-
### Description
I came across with some trouble in generating training data using t2t-datagen. The tokenizes are messy.
![image](https://user-images.githubusercontent.com/32641072/54520210-2756af0…
-
Hey,
I try to experiment with the Transformer-Decoder Memory Compressed Attention model from .
I'm wondering if the following HParams are relevant/enough to reproduce
```
@registry.register_hp…
-
Dear community, I’m new to T2T … thank you for providing the framework and the documentation! I was following [a tutorial to start training](https://medium.com/data-from-the-trenches/training-cutting-…
-
Hey pals,
This is what I am trying to replicate...
pip install tensor2tensor
# See what problems, models, and hyperparameter sets are available.
# You can easily swap between them (and…
-
I have trained a base transformer model using the sub-word segmentation approach of Sennrich et al. (https://github.com/rsennrich/subword-nmt). This requires me to set the subword_tokenizer in the new…