Skip to content

Small experiment on batch sizes for umbalanced datasets

Notifications You must be signed in to change notification settings

LucaCappelletti94/udbnn

Repository files navigation

udbnn

Travis CI build SonarCloud Quality SonarCloud Maintainability Codacy Maintainability Maintainability Pypi project Pypi total project downloads

Experiment to determine whetever a large batch-size can be helpful with extremely umbalanced datasets.

How do I install this package?

As usual, just download it using pip:

pip install udbnn

Tests Coverage

Since some software handling coverages sometime get slightly different results, here's three of them:

Coveralls Coverage SonarCloud Coverage Code Climate Coverate

How do I run the experiments?

Since the experiments take quite a bit to run, I suggest you to run them while in a TMUX-like environment. If available, you should consider using a computer with a tensorflow-compatible GPU.

Then just run with a python shell:

from udbnn import run
run("dataset")

About

Small experiment on batch sizes for umbalanced datasets

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages