-
Notifications
You must be signed in to change notification settings - Fork 188
Open
Description
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.
- I create a network using tinn and I train it
- I build a network that should be the same in Keras than with Tinn
- Then a train it inside keras and display the weights and bias
- 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?
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels