search

tensorflow / tensor2tensor

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
Apache License 2.0
15.52k stars 3.5k forks source link

how to run the customised data #1701

Open newmluser opened 5 years ago

newmluser commented 5 years ago

Description

I have 2 files which are input (in one laguage) and output (in another language). I have converted them into numers. all the file is having 20K lines with numbers and converted output file also 20K with converted numbers in the file. I was thinking of using seq2seq. having some issues and want to try this. Can you help me how to do that. The input file content will be : Example 12 22 33 44 55 11 33 44 6666 888 99999 2222 4444 5555 7777 ..like that and output file is 4 5 6 7 8 9 1 11 112 222 124 1224 5656 7878 990

Environment information

windows10

OS: <your answer here>

$ pip freeze | grep tensor
mesh-tensorflow==0.0.5
tensor2tensor==1.14.0
tensor2tensor==1.14.0
tensorboard==1.14.0
tensorflow==2.0.0b1
tensorflow-datasets==1.2.0
tensorflow-estimator==1.14.0
tensorflow-gan==1.0.0.dev0
tensorflow-metadata==0.14.0
tensorflow-probability==0.7.0

python -V
Python 3.7.3```

### For bugs: reproduction and error logs

Steps to reproduce:

how to run t2t-trainer in windows?
I see that scipts folder have it and can run this.
how can I give the options for my customized data where I have the input file and outfile .

Error logs:

...

abnf commented 5 years ago

This tutorial teaches how to use custom text models. Just follow the guidelines of the train locally section instead of on ML Engine.

https://cloud.google.com/blog/products/gcp/cloud-poetry-training-and-hyperparameter-tuning-custom-text-models-on-cloud-ml-engine