# andersbll/deeppy

Deep learning in Python

Repository: https://github.com/andersbll/deeppy
Canonical: https://ross.abutalabs.com/products/deeppy
Language: Python
License: MIT
License Family: permissive
Last push: 2020-12-28T11:51:42+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4367, "days_push": 2074, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1370, forks 297 (observed 2026-08-28T04:04:31.860138+00:00)

## What it is
DeepPy is a Pythonic deep learning framework built on top of NumPy, with optional CUDA acceleration via the cudarray library. It provides a lightweight, educational approach to defining and training neural networks in Python.

## Use cases
- train neural networks in python
- learn how deep learning frameworks work internally
- build neural networks on top of numpy
- experiment with gpu-accelerated numpy arrays
- implement a small deep learning model from scratch

## When to choose
- you want a minimal, readable codebase for learning deep learning internals
- you need a simple NumPy-based neural network framework for experimentation

## When to avoid
- you need a production-ready framework with active maintenance and community support
- you require modern features like automatic differentiation graphs, distributed training, or transformer support
- you need up-to-date CUDA hardware support

## Facets
- artifact type: framework
- maturity: abandoned
- function: deep-learning, machine-learning, gpu-computing
- domain: deep-learning, machine-learning
- platform: python
- tags: numpy, neural-networks, cuda, gpu

## Member repositories
- andersbll/deeppy (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:31.860138+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:40:54.023903+00:00, confidence not recorded.
  - readme: https://github.com/andersbll/deeppy (fetched 2026-08-28T04:04:31.860138+00:00, sha 74fb623c150c)
- Data as of 2026-08-30T08:39:29.467469+00:00.