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

MLP demo #8

Merged
merged 1 commit into from Aug 18, 2017
Merged

MLP demo #8

merged 1 commit into from Aug 18, 2017

Conversation

jaderiverstokes
Copy link
Contributor

Demo for the MLP module using MNIST data.

@fmcquillan99
Copy link

This is a really great demo workbook, thanks for posting.

Suggestions

  1. concat does not work for greenplum, perhaps do:

SELECT round(count(*)*100/60000.0,2) as train_accuracy_percent from
(select mnist_train.y as actual, mnist_train_prediction.estimated_y as estimated
from mnist_train_prediction inner join mnist_train
on mnist_train.id=mnist_train_prediction.id) q
WHERE q.actual=q.estimated;

  1. Can you please add a comment at the top on the parameters you used to get a good accuracy + the platform you used?

@jaderiverstokes
Copy link
Contributor Author

Added those few changes. Should be good to merge now. I'm not sure how these demos are typically presented, but note that this demo relies on the newly created data directory in this repo. This is mentioned in the notebook itself.

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