04/03/2023, 2:19 PM
*Julia Beliaeva*  [21 h 06]
Hi, no, it's not possible right now. You'll need to train your model elsewhere and convert it to onnx format to use with KotlinDL in Android.
Was an answer provided 3 months ago ... is it still current ? I mean : will it be a version of Kotlin DL allowing you to train a model, from scratch, within an Android phone , using local data,? because in fact, i believe .. this is the “graal”, most of us are waiting for ! then the next question is : can we write code using current kotlin-DL .. that will run calculations used in a training process ? by advance thanks a lot for your help Vinz


04/04/2023, 4:30 PM
I suppose that we have no on the roadmap the training model on the android with the local data. But, could you share some use cases for training models from scratch on Android? What is the domain and nature of data? Is this tabular data or images or videos or text?


04/05/2023, 6:56 AM
I hope it could be time series data, or data coming from phone api’s like energy , cpu, memory, consumption, gsm signal strength, type of network traffic, gps position,
The thing is, we have no tools to run ‘epochs’ on smartphones , and i do not know if there are python frameworks (pytyorch, scikitlearn, and so on ..) being able to be launched on android systems