autonomio/talos
Hyperparameter Experiments with TensorFlow and Keras
This tool helps researchers, data scientists, and data engineers efficiently find the best settings for their machine learning models built with TensorFlow or Keras. It takes your model code and a range of parameter choices, then automatically runs and evaluates many experiments. The output is a highly optimized model that performs better on prediction tasks.
1,636 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are building deep learning models and want to automate the tedious process of finding optimal hyperparameters without losing control over your model architecture.
Not ideal if you are not using TensorFlow, Keras, or PyTorch for your deep learning models.
Stars
1,636
Forks
266
Language
Python
License
MIT
Category
Last pushed
Apr 22, 2024
Commits (30d)
0
Dependencies
11
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/autonomio/talos"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
optuna/optuna
A hyperparameter optimization framework
keras-team/keras-tuner
A Hyperparameter Tuning Library for Keras
KernelTuner/kernel_tuner
Kernel Tuner
syne-tune/syne-tune
Large scale and asynchronous Hyperparameter and Architecture Optimization at your fingertips.
deephyper/deephyper
DeepHyper: A Python Package for Massively Parallel Hyperparameter Optimization in Machine Learning