77axel/PyCNN
A Python library to easily build, train, and test your CNN AI models.
This is a Python library for developers to build, train, and test Convolutional Neural Network (CNN) models for image classification tasks. It takes structured image datasets as input (either local folders or Hugging Face datasets) and outputs trained models that can classify new images and be exported to PyTorch. This tool is designed for machine learning engineers and researchers who want fine-grained control over their CNN implementations without relying on high-level deep learning frameworks.
Use this if you are a developer looking to implement and experiment with CNNs from scratch using low-level libraries like NumPy, or if you need to export your custom CNN models to PyTorch.
Not ideal if you are a beginner looking for a high-level deep learning framework (like TensorFlow or PyTorch) to quickly build and deploy models, or if you don't have programming experience.
Stars
21
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jan 16, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/77axel/PyCNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Dobiasd/frugally-deep
A lightweight header-only library for using Keras (TensorFlow) models in C++.
flashlight/flashlight
A C++ standalone library for machine learning
wichtounet/dll
Fast Deep Learning Library (DLL) for C++ (ANNs, CNNs, RBMs, DBNs...)
NVlabs/tiny-cuda-nn
Lightning fast C++/CUDA neural network framework
KasperskyLab/knp
Kaspersky Neuromorphic Platform