Kotlin/kotlindl

Health v2 · maintenance only

Adoption not part of the score

1576 stars · 113 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

deep-learning machine-learning llm-training deep-learning machine-learning jvm keras-inspired tensorflow onnx transfer-learning kotlin jvm android gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Kotlin/kotlindl")