pranftw/neowise
Deep Learning library built from scratch with Python and NumPy
This library helps software developers build and experiment with deep learning models from the ground up. It takes numerical data (like images or text converted to numbers) and allows you to define a neural network architecture, train it, and then evaluate its performance. It's for Python developers who want to understand the core mechanics of deep learning without relying on higher-level frameworks.
No commits in the last 6 months.
Use this if you are a Python developer looking to build deep learning models from scratch for educational purposes or to gain a deeper understanding of neural network mechanics.
Not ideal if you need to deploy production-ready deep learning models quickly, use GPUs, or leverage pre-built, complex architectures.
Stars
14
Forks
1
Language
Python
License
MIT
Category
Last pushed
Aug 14, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pranftw/neowise"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
digantamisra98/Mish
Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]
Sentdex/nnfs_book
Sample code from the Neural Networks from Scratch book.
itdxer/neupy
NeuPy is a Tensorflow based python library for prototyping and building neural networks
vzhou842/cnn-from-scratch
A Convolutional Neural Network implemented from scratch (using only numpy) in Python.
nicklashansen/rnn_lstm_from_scratch
How to build RNNs and LSTMs from scratch with NumPy.