Today I want to share with you my presentation about an upcoming 0.2 KotlinDL release (0.2-alpha-1 artifact is available now on Maven Central). Currently, the KotlinDL framework can boast that this is the only way to construct and train complex neural networks on JVM, such as VGG, ResNet, or MobileNet. There is also support for transfer learning for the popular models trained in Keras (or available in Keras. applications). For image preprocessing, several functions are available that allow you to avoid complex and routine work on the JVM. Code from the demo: https://github.com/zaleslaw/KotlinDL-Demo/tree/demo-1 Library: https://github.com/JetBrains/KotlinDL P.S. Support our project with a star on Github!

@zaleslaw why is it not possible to build those architectures with dl4j?

Never see Mobilenet built with dl4j

what does mobilenet exatly use that you cannot reproduce?

So, I have a production experience with Dl4j in 2017-18, as I remember it was really hard to describe there huge models, prepocess data, load weights from keras for transfer learning. Now, I don't know anyone who use it in production and have no information about project roadmap, and I did not keep in mind this framework when writing the marketing words above, but means modern frameworks as Java API for tf, PyTorch Java API from Facebook, tribuo and Java bindings for onnx runtime

OK fair enough, the java API for tf and torch are for inference only I guess (at least the "documented" part indeed)

It's possible, he is old player in this field, and highly likely worked in Skymind

@zaleslaw thank you a lot - I plan (with hopefully a student) to start working on that very seriously in July.

So, ping me, if you need a collaborator here

Wonderful - I will certainly do 🤗