l11x0m7/lightnn
The light deep learning framework for study and for fun. Join us!
This is a lightweight deep learning framework designed to help Python developers understand and experiment with core deep learning concepts. It allows you to build neural networks from basic components like layers, activation functions, and optimizers. You can input your data and network architecture, and it will output trained models that can perform tasks like image classification or language modeling. It's intended for those learning deep learning principles or wanting to build simple models from scratch.
110 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are a Python developer or student who wants to learn the fundamental mechanics of deep learning by building models from the ground up without relying on complex, high-level libraries.
Not ideal if you need a production-ready framework for large-scale, high-performance deep learning projects or if you prefer a framework with extensive community support and advanced features.
Stars
110
Forks
32
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 30, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/l11x0m7/lightnn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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, ...)