Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

model is not predicted the words present in data set #5

Open
vinaykumarbundla opened this issue Oct 27, 2017 · 1 comment
Open

model is not predicted the words present in data set #5

vinaykumarbundla opened this issue Oct 27, 2017 · 1 comment
Assignees

Comments

@vinaykumarbundla
Copy link

1.When I trained language translation model using Recurrent Neural networks,the model is predicting unknown to some words even if the words are present in the data set..

2.Model is translating wrong, even if the word is present in the data set

I am using Tensor flow 1.2 v and data set size 100 MB
hyper parameters:

hidden units=256
learning_rate = 5 e-3
batch_size = 64
epochs = 7000

Can any one please resolve me?

@Nemzy Nemzy self-assigned this Oct 27, 2017
@Nemzy
Copy link
Owner

Nemzy commented Nov 3, 2017

Hi @vinaykumarbundla ,

See #4.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants