# Kotlin/kotlindl

High-level Deep Learning Framework written in Kotlin and inspired by Keras

Repository: https://github.com/Kotlin/kotlindl
Canonical: https://ross.abutalabs.com/products/kotlindl
Language: Kotlin
License: Apache-2.0
License Family: permissive
Topics: gpu, tensorflow, deeplearning, kotlin
Last push: 2024-05-31T08:05:58+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2352, "days_push": 824, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1576, forks 113 (observed 2026-08-28T04:05:05.994562+00:00)

## What it is
KotlinDL is a high-level deep learning framework written in Kotlin and inspired by Keras, built on top of the TensorFlow Java API and ONNX Runtime. It enables JVM and Android developers to train models from scratch, run inference with Keras/ONNX models, and apply transfer learning with pre-trained models.

## Use cases
- train a neural network in Kotlin
- run ONNX model inference on the JVM
- import a Keras model for inference in a JVM app
- apply transfer learning to a pre-trained image model
- deploy a deep learning model in an Android app
- build a CNN like LeNet for image classification

## When to choose
- you are a Kotlin/JVM or Android developer wanting a Keras-like deep learning API
- you need to run Keras or ONNX models for inference on the JVM
- you want transfer learning with pre-trained models in Kotlin

## When to avoid
- you need cutting-edge research features or the latest model architectures
- you work primarily in Python with the native TensorFlow/PyTorch ecosystems
- you need a framework with frequent releases and a large community

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, machine-learning, llm-training
- domain: deep-learning, machine-learning
- platform: jvm
- tags: keras-inspired, tensorflow, onnx, transfer-learning, kotlin, jvm, android, gpu

## Member repositories
- Kotlin/kotlindl (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:05.994562+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 2026-08-30T03:57:12.224229+00:00, confidence not recorded.
  - readme: https://github.com/Kotlin/kotlindl (fetched 2026-08-28T04:05:05.994562+00:00, sha 185f38ed871a)
- Data as of 2026-08-30T08:39:29.467469+00:00.