Skip to content

[CVPR 2024] Efficient Hyperparameter Optimization with Adaptive Fidelity Identification

License

Notifications You must be signed in to change notification settings

jjiantong/FastBO

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

[CVPR 2024] Efficient Hyperparameter Optimization with Adaptive Fidelity Identification

FastBO is implemented based on Syne Tune.

How to use

Install FastBO: install everything in a virtual environment st_venv.Remember to activate this environment before working with FastBO. We also recommend building the virtual environment from scratch now and then, in particular when you pull a new release, as dependencies may have changed.

git clone https://github.com/jjiantong/FastBO.git
cd FastBO
python3 -m venv st_venv
. st_venv/bin/activate
pip install --upgrade pip
pip install -e '.[extra]'

Quick start for a simple example: run Bayesian Optimization with 4 workers on a local machine. Please note that you have to report metrics from a training script so that they can be communicated later to FastBO. The training script for this example is experiments/lcbench_bo.py.

cd experiments
python3 lcbench_bo.py

Basic ideas

About

[CVPR 2024] Efficient Hyperparameter Optimization with Adaptive Fidelity Identification

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published