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

not able to run tf_example.py on test data #1

Open
neuwirtter opened this issue May 9, 2024 · 2 comments
Open

not able to run tf_example.py on test data #1

neuwirtter opened this issue May 9, 2024 · 2 comments

Comments

@neuwirtter
Copy link

neuwirtter commented May 9, 2024

Dear developers,

I have tried to use your python script to run tf_example.py model on testing data provided and I've been encountering these error (please see the screeshot, last two errors) - first I solved with modification of the input shape variable (or I thought so: input_shape = (len(seqs.iloc[0]) * len(mbe.AA_ORDER),)) but now I keep getting the second one. Could you please advise on what am I doing wrong?
Snímek obrazovky 2024-05-09 v 13 50 48

@apbusia
Copy link
Owner

apbusia commented May 16, 2024

Hello!

I haven't been able to reproduce these issues on my end --- the code currently in the repo is running for me without producing errors.

However, I searched around and was able to find reports of some similar errors (for example, here). Based on this, I'd advise you try either (a) updating the default value for epsilon in make_ann_classifier to a real value (1e-7 seems to be the current default value in the docs), or (b) removing the epsilon and/or clipvalue arguments from tfk.optimizers.Adam. Although I cannot reproduce the errors, I can confirm that the script still runs for me with either of these changes.

@neuwirtter
Copy link
Author

neuwirtter commented May 17, 2024 via email

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

2 participants