Kinho

github.com/kinhosz/Neural Developer Tools Open-source projectOpen source

Kinho’s Neural repository provides an API for deep learning and feedforward neural network models.

github.com/kinhosz/Neural
Kinho homepage screenshot

About Kinho

Kinho's Neural is a Python API for creating feedforward neural networks. The Neural class, imported from the Kinho package, supports defining layer sizes, loading a pre-trained .brain file, running inference with send(), training with learn() using backpropagation, and exporting models.

It requires Python below 3.12 and requires either sizes or brain_path to initialize. It also provides settings for learning rate, GPU use, mini-batch size, and multilabel output.

Key features

  • Define feedforward network by layer sizes in constructor
  • Load pre-trained model from .brain file path
  • Run inference with send() returning per-label probabilities
  • Train with learn() using backpropagation to update weights
  • Export trained model to file with filename and path
  • Configure learning rate, GPU use, mini-batch size, multilabel
Best for: Python developers who want to define, train, and run feedforward neural networks in code.
Good for
  • Installs with pip install Kinho
  • Combines model definition, training, inference, and export in one class
  • Supports pre-trained .brain files with GPU and mini-batch settings
Watch out for
  • Requires Python version below 3.12
  • Initialization fails with type error without sizes or brain_path
  • If both sizes and brain_path are passed, sizes is ignored

Kinho at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 6, 2026 · Online when checked
Listed
Oct 5, 2026

Kinho alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in Developer Tools

Well-known listings from the same topic.

All 423

Kinho FAQ

How do I install Kinho?
Use pip install Kinho with Python version below 3.12.
What is required to create a Neural network?
You must pass either sizes or brain_path, otherwise a type error is generated. If both are passed, brain_path takes priority.
What does send() return?
A list with the same size as the output layer, with a probability for each label; the highest probability is the prediction.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing