-
Is is okay to use random sampled data which is saved before the training?
I mean, should it have to be changed every epoch?
-
https://github.com/tensorflow/tensor2tensor/blob/2f8423a7daf39c549fa4f87d369d3ff95e719e6c/tensor2tensor/models/research/universal_transformer_util.py#L1207
Is this supposed to be "(previous_state *…
-
When trying to freeze my trained model I get the following error:
```
Traceback (most recent call last):
File "/home/emil/Dokumente/RaspberryPi/Francis/g2p-test/venv/bin/g2p-seq2seq", line 11, in…
-
Using command:
```
t2t-decoder \
> --t2t_usr_dir=~/bAbI-T2T/t2t_usr_dir \
> --data_dir=~/babi_data/data \
> --output_dir=~/babi_data/outpu \
> --problem=babi_qa_sentence_task1_10k \
>…
-
That's a pretty interesting project. I'm currently using C `Kakasi` for Kanji to Romaji Japanese transliteration, so I did a wrapper to Node.js for that - [Kakasi.js](https://github.com/loretoparisi/k…
-
[awesome-transformer](https://github.com/SkyAndCloud/awesome-transformer), should classified into `Deep Learning`。
Transformer is a powerful model applied in sequence to sequence learning. However, w…
-
#
*help*
### Description
Hi，I have trained the transformer model，
PROBLEM=translate_ende_wmt32k
MODEL=transformer
HPARAMS=transformer_base_single_gpu
But I want to get the word embedding resul…
-
-
Hello, when I run ”bash compare_gan_prepare_datasets.sh“， I got the error "tensor2tensor not found!". Clearly, there does not exist anything called t2t-datagen in the folder $HOME/.local/bin. So how c…
-
### Description
I've tried to reproduce the training procedure for the speech transformer model (https://github.com/tensorflow/tensor2tensor/blob/master/docs/tutorials/asr_with_transformer.md) but en…