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

Import bias and weight from Keras #22

Open
kasey- opened this issue May 4, 2019 · 0 comments
Open

Import bias and weight from Keras #22

kasey- opened this issue May 4, 2019 · 0 comments

Comments

@kasey-
Copy link

kasey- commented May 4, 2019

Hello,

I am trying to train a network using keras and importing his weight and bias inside Tinn to be able to benefit from the keras environment.

  1. I create a network using tinn and I train it
  2. I build a network that should be the same in Keras than with Tinn
  3. Then a train it inside keras and display the weights and bias
  4. I put the weights + bias inside a Tinn model and load them

But the network is unsuccessfully predicting the output

Here my code I used in all my Keras layer a Sigmoid activation function which should lead to the same result KerasTinn.zip But I get two bias for every layers from Keras and none of them works correctly. I am neither sure the order of the weights is correct.

Any idea how to solve this?

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

No branches or pull requests

1 participant