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.

Sign up for GitHub

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

Jump to bottom

use hyperband / bayesian probability for tuner instead of RandomSearch #276

Open
Palashio opened this issue Jul 19, 2020 · 0 comments
Open

use hyperband / bayesian probability for tuner instead of RandomSearch #276

Palashio opened this issue Jul 19, 2020 · 0 comments
Labels
core-ai
Projects
Contribution Queue

Comments

@Palashio
Copy link
Owner

currently we're using random-search from keras-tuner. Instead we should be using probabilistic models
@Palashio Palashio added this to To do in Contribution Queue Jul 19, 2020
kamranmajid41 added a commit to kamranmajid41/libra that referenced this issue Jul 31, 2020
@kamranmajid41
name: b) CNN feature map visualization about: User now has option to …
55b140a 
…visualize feature map associated with CNN after calling convolutional_query() labels: feature

This pull request closes Palashio#276 .  - What I did : changed the CNN tuner from using randomsearch to hyperband  - How I did it : changed from randomsearch to hyperband and altered parameters.  - How to verify it : Pass a dataset to the client function and build the model. This pull request alters an existing feature within libra. @Palashio, could you please take a look at it?
@kamranmajid41 kamranmajid41 mentioned this issue Jul 31, 2020
Closed
1 task
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
core-ai
Projects
Contribution Queue
  
To do
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Hyperband Implemented in Place of RandomSearch kamranmajid41/libra
1 participant
@Palashio