[D] Efficient ways of choosing number of layers/neurons in a neural network

1. hyperopt

   1 15 7,399 3.5 Python

   Distributed Asynchronous Hyperparameter Optimization in Python

   

   optuna, hyperopt, nni, plenty of less-known tools too.

2. Judoscale

   judoscale.com featured

   Save 47% on cloud hosting with autoscaling that just works. Judoscale integrates with Django, FastAPI, Celery, and RQ to make autoscaling easy and reliable. Save big, and say goodbye to request timeouts and backed-up task queues.

   

3. nni

   2 5 13,991 1.8 Python

   Discontinued An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

   

   optuna, hyperopt, nni, plenty of less-known tools too.

4. optuna

   3 35 11,798 9.9 Python

   A hyperparameter optimization framework

   

   optuna, hyperopt, nni, plenty of less-known tools too.

Suggest a related project