elena-ecn/optuna-optimization-for-PyTorch-CNN
Hyperparameter optimization study for a PyTorch CNN with Optuna.
This project helps machine learning engineers and researchers automatically find the best settings for their PyTorch Convolutional Neural Networks. It takes a CNN model and a dataset like MNIST, then explores different optimizers, learning rates, and network architectures. The output is a summary of the best-performing hyperparameters and their impact on model accuracy, saved to a CSV file.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher looking to systematically optimize the hyperparameters of a PyTorch CNN to achieve maximum test accuracy for image classification tasks.
Not ideal if you are not working with PyTorch CNNs, need to optimize for very different types of models, or are not interested in automated hyperparameter tuning.
Stars
21
Forks
2
Language
Python
License
MIT
Category
Last pushed
Nov 29, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/elena-ecn/optuna-optimization-for-PyTorch-CNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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