Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
High-level Deep Learning Framework written in Kotlin and inspired by Keras
| Date | Stars |
|---|---|
| 2026-07-24 | 1574 |
| 2026-07-25 | 1574 |
| 2026-07-28 | 1574 |
| 2026-07-30 | 1574 |
| 2026-07-31 | 1573 |
| 2026-08-06 | 1573 |
Today
— stars today
This week
-1 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# KotlinDL: High-level Deep Learning API in Kotlin [](https://confluence.jetbrains.com/display/ALL/JetBrains+on+GitHub)
[](http://kotlinlang.org)
[](https://kotlinlang.slack.com/messages/kotlindl/)
KotlinDL is a high-level Deep Learning API written in Kotlin and inspired by [Keras](https://keras.io).
Under the hood, it uses TensorFlow Java API and ONNX Runtime API for Java. KotlinDL offers simple APIs for training deep learning models from scratch,
importing existing Keras and ONNX models for inference, and leveraging transfer learning for tailoring existing pre-trained models to your tasks.
This project aims to make Deep Learning easier for JVM and Android developers and simplify deploying deep learning models in production environments.
Here's an example of what a classic convolutional neural network LeNet would look like in KotlinDL:
```kotlin
private const val EPOCHS = 3
private const val TRAINING_BATCH_SIZE = 1000
private const val NUM_CHANNELS = 1L
private const val IMAGE_SIZE = 28L
private const val SEED = 12L
private const val TEST_BATCH_SIZE = 1000
private val lenet5Classic = Sequential.of(
Input(
IMAGE_SIZE,
IMAGE_SIZE,
NUM_CHANNELS
),
Conv2D(
filters = 6,
kernelSize = intArrayOf(5, 5),
strides = intArrayOf(1, 1, 1, 1),
activation = Activations.Tanh,
kernelInitializer = GlorotNormal(SEED),
biasInitializer = Zeros(),
padding = ConvPadding.SAME
),
AvgPool2D(
poolSize = intArrayOf(1, 2, 2, 1),
strides = intArrayOf(1, 2, 2, 1),
padding = ConvPadding.VALID
),
Conv2D(
filters = 16,
kernelSize = intArrayOf(5, 5),
strides = intArrayOf(1, 1, 1, 1),
activation = Activations.Tanh,
kernelInitializer = GlorotNormal(SEED),
biasInitializer = Zeros(),
padding = ConvPadding.SAME
),
AvgPool2D(
poolSize = intArrayOf(1, 2, 2, 1),
strides = intArrayOf(1, 2, 2, 1),
padding = ConvPadding.VALID
),
Flatten(), // 3136
Dense(
outputSize = 120,
activation = Activations.Tanh,
kernelInitializer = GlorotNormal(SEED),
biasInitializer = Constant(0.1f)
),
Dense(
outputSize = 84,
activation = Activations.Tanh,
kernelInitializer = GlorotNormal(SEED),
biasInitializer = Constant(0.1f)
),
Dense(
outputSize = 10,
activation = Activations.Linear,
kernelInitializer = GlorotNormal(SEED),
biasInitializer = Constant(0.1f)
)
)
fun main() {
val (train, test) = mnist()
lenet5Classic.use {
it.compile(
optimizer = Adam(clipGradient = ClipGradientByValue(0.1f)),
loss = Losses.SOFT_MAX_CROSS_ENTROPY_WITH_LOGITS,
metric = Metrics.ACCURACY
)
it.logSummary()
it.fit(dataset = train, epochs = EPOCHS, batchSize = TRAINING_BATCH_SIZE)
val accuracy = it.evaluate(dataset = test, batchSize = TEST_BATCH_SIZE).metrics[Metrics.ACCURACY]
println("Accuracy: $accuracy")
}
}
```
## Table of Contents
- [Library Structure](#library-structure)
- [How to configure KotlinDL in your project](#how-to-configure-kotlindl-in-your-project)
- [Working with KotlinDL in Android projects](#working-with-kotlindl-in-android-projects)
- [Working with KotlinDL in Jupyter Notebook](#working-with-kotlindl-in-jupyter-notebook)
- [KotlinDL, ONNX Runtime, Android, and JDK versions](#kotlindl-onnx-runtime-android-and-jdk-versions)
- [Documentation](#documentation)
- [Examples and tutorials](#examples-and-tutorials)
- [Running KotlinDL on GPU](#running-kotlindl-on-gpu)
- [Logging](#logging)
- [Fat Jar issue](#fat-jar-issuExcerpt of 18,229 characters
Read on GitHub
426
193
31
17
Maria Khalusova · Unstructured.io · Canada
10
9
6
5
3
3
2
2
2
1
1
Xa9aX ツ
1
1
1
1
Onuralp SEZER · @ultralytics · Turkey
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:69750f4be48a520a, topic:tensorflow, desc:deep learning framework
matched fp:69750f4be48a520a, topic:gpu