# pluskid/Mocha.jl

Deep Learning framework for Julia

Repository: https://github.com/pluskid/Mocha.jl
Canonical: https://ross.abutalabs.com/products/mochajl
Language: Julia
License: NOASSERTION
License Family: other
Last push: 2018-12-06T01:09:35+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4331, "days_push": 2828, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1284, forks 244 (observed 2026-08-28T04:04:14.546245+00:00)

## What it is
Mocha.jl is a deep learning framework for Julia, inspired by Caffe, providing modular layers, solvers, and support for training convolutional neural networks with optional unsupervised pre-training. It was officially deprecated in December 2018 and only works with Julia v0.6.

## Use cases
- train convolutional neural networks in Julia
- deep learning framework for Julia
- stochastic gradient descent solver for neural networks
- unsupervised pre-training with stacked autoencoders
- legacy Julia 0.6 deep learning codebase

## When to choose
- maintaining or reading an existing legacy Mocha.jl codebase on Julia 0.6
- studying the architecture of an early Julia deep learning framework

## When to avoid
- starting any new deep learning project in Julia
- using Julia 1.0 or later
- needing GPU kernels or modern autodifferentiation
- wanting an actively maintained framework

## Facets
- artifact type: framework
- maturity: abandoned
- function: deep-learning, machine-learning, gpu-computing
- domain: deep-learning, machine-learning
- platform: cross-platform
- tags: neural-networks, caffe-inspired, deprecated, convolutional-networks, autoencoders, julia, gpu

## Member repositories
- pluskid/Mocha.jl (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:14.546245+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 2026-08-30T04:56:46.201105+00:00, confidence not recorded.
  - readme: https://github.com/pluskid/Mocha.jl (fetched 2026-08-28T04:04:14.546245+00:00, sha 3b05f501c68a)
- Data as of 2026-08-30T08:39:29.467469+00:00.