-
Notifications
You must be signed in to change notification settings - Fork 2k
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
add Approximating non function mapping example #1440
add Approximating non function mapping example #1440
Conversation
python autogen.py add_example keras_recipes/approximating_non_function_mappings
Fix patience. Fix limits. Add tfp link.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I put a bunch of fixes in this PR:
LukeWood#2, Please merge, lgtm.
I wasn't able to push it directly to your branch.
Do new files need to be added to index pages for keras.io?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@fchollet I think this looks pretty good - @MarkDaoust added some edits.
I left a few final copy-edits on my own wording which I can apply later today - but let me know if this is a good addition.
Edit: sorry, misunderstood Mark's comment. Merged his PR on my repo.
Approximatingfunctions
@MarkDaoust I merged them - let me know if anything else is needed! |
FYI @MarkDaoust you may want to re-generate the markdown, the learned MDN is pretty poor here - and I've been able to get much stronger convergences. Maybe we can just run it 1-2 more times to get good figures |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM.
@LukeWood did you want to add those copy edits and regenerate, or should I just merge this? |
Go ahead @MarkDaoust - I think the point is still clear and I'm happy with it. Cheers! |
This guide covers how to approximate non-function one to many mappings using Keras Core: https://colab.research.google.com/drive/1kRYIn8lMuvK8wc9uloEwJvZ7foTUNPnV?usp=sharing
PTAL!