-
请问，我在最新的tensor2tensor版本上跑您的程序，出现以下错误，莫非是版本问题，可以帮忙看看吗？
谢谢！
/t2t_wmt$ sh ./main/gen_base.sh
Building prefix dict from the default dictionary ...
Loading model from cache /tmp/jieba.cache
Loading mo…
-
### Description
> t2t-exporter won't export models trained as _packed.
### *TensorFlow* and *tensor2tensor* versions
> tensor2tensor==1.5.5
tensorboard==1.5.0
tensorflow==1.5.0
ten…
-
Hello, thanks for releasing this code! I need to pretrain a BERT model for non-English language using my own (domain-specific) data. I noticed that the training code for WordPiece vocabulary is not re…
-
Hi all,
I was trying to keep the input/output vocabularies separated (to have an additional datapoint and check performances).
I took inspiration from `wsj_parsing_tokens_16k` - basically by using…
-
### Description
I will to use my own set of data, but it is not working. Could anyone can help with this issue?
### Environment information
```
OS: CentOS
$ pip freeze | grep tensor
tens…
-
When running the command line program or even the tests with `python setup.py test` i get the following error:
```
running test
running egg_info
writing requirements to g2p_seq2seq.egg-info/requir…
-
Hi, I have been looking at the code in layers.common_attention.dot_product_attention, this seems to be a regular dot product attention without scaling (there is no other attention mechanism that imple…
-
Hi, we have trained several models with the same configure on NMT, and we want to ensemble these models when decode (just combine the probability of each word in each decode step). But it seems curre…
-
### Description
Weights are unable to initialize for the symbol modality due to reuse being set to true in line 146 of modalities.py. Setting reuse to tf.AUTO_REUSE allows the weights to initialize w…
-
Hi,
---------------------------------
Ubuntu 1604
MiniConda3
Python3.6.5
TensorFlow1.8.0
---------------------------------
I've cloned this repo and used `python -m pip install -e . --user` in…