RootHarold/Lycoris
A lightweight and easy-to-use deep learning framework with neural architecture search.
Lycoris helps developers build machine learning models more efficiently by automating the process of finding the best neural network architecture. You provide your data, and it automatically explores different network configurations to identify a high-performing model for classification or prediction tasks. This tool is for software engineers and machine learning practitioners who implement custom deep learning solutions.
175 stars. No commits in the last 6 months.
Use this if you are a developer building deep learning models and want to automate the complex and time-consuming task of neural network architecture search to achieve better model performance with less manual effort.
Not ideal if you are an end-user looking for a no-code machine learning solution or a framework with extensive GPU support, as this currently focuses on CPU-based computation.
Stars
175
Forks
2
Language
C++
License
—
Category
Last pushed
May 22, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/RootHarold/Lycoris"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
keras-team/keras
Deep Learning for humans
Lightning-AI/torchmetrics
Machine learning metrics for distributed, scalable PyTorch applications.
Lightning-AI/pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
lanpa/tensorboardX
tensorboard for pytorch (and chainer, mxnet, numpy, ...)