Ch0ser/Deepflows
DeepFlows is a lightweight deep learning framework for teaching and experimentation. It includes tensor encapsulation, automatic differentiation, backend abstraction, common neural network modules and optimizers, as well as some example training scripts and service modules.
DeepFlows is a beginner-friendly deep learning framework designed to help students and researchers understand how neural networks work. It allows you to define neural network models, train them with your data (like image datasets such as MNIST or CIFAR-10), and see how they perform. This is ideal for those learning or experimenting with deep learning concepts rather than deploying production systems.
Use this if you are a student, educator, or researcher who wants to learn, teach, or experiment with deep learning concepts from scratch, or quickly test new ideas.
Not ideal if you need a robust, high-performance framework for large-scale production deployments or complex research requiring advanced features and extensive community support.
Stars
38
Forks
2
Language
Python
License
MIT
Category
Last pushed
Feb 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Ch0ser/Deepflows"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pymc-devs/pytensor
PyTensor allows you to define, optimize, and efficiently evaluate mathematical expressions...
arogozhnikov/einops
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
lava-nc/lava-dl
Deep Learning library for Lava
tensorly/tensorly
TensorLy: Tensor Learning in Python.
tensorpack/tensorpack
A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility