Help. How to Convert DeepXDE model to TensorflowLite model. #1744
Unanswered
Afiqah-Nur
asked this question in
Q&A
Replies: 1 comment
-
|
I have no experience with TensorflowLite. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Hi. After going through all FAQs and issues, I learned that DeepXDE model can be saved through ckpt files. And I have successfully done that.
However, Im trying to convert the model to tensorflowlite model. By following the tutorials from here: tensorflow/tensorflow#61645 using the ckpt file saved during training DeepXDE.
When I run the model saved, the result was very inaccurate. Perhaps, the model architecture is not correct? Is there any other way to do this? Or if I were to rebuild the model using deepxde.nn.tensorflow_compat_v1.FNN, how to correctly use the the class in conjunction with TensorFlow's tf.train.Checkpoint? I'm including my code snippets below.
Please help me.



Beta Was this translation helpful? Give feedback.
All reactions