joeddav/devol

Genetic neural architecture search with Keras

46
/ 100
Emerging

This tool helps machine learning engineers and researchers automatically design the optimal neural network architecture for classification problems. You provide your dataset and define the constraints for your model's structure, and it uses genetic algorithms to evolve and test many different configurations. The output is a highly tuned Keras model that performs well on your specific classification task, along with insights into which architectural choices are most effective.

952 stars. No commits in the last 6 months.

Use this if you need to find the best deep learning model architecture for a classification problem without manually trying countless configurations, and you have significant computational resources available.

Not ideal if you have very limited computational power or are working on problems other than classification, as the process of evaluating many models can be very resource-intensive.

deep-learning-architecture image-classification neural-network-design model-optimization machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

952

Forks

114

Language

Python

License

MIT

Last pushed

May 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/joeddav/devol"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.