Hi, community, will make a presentation today abou...
# kotlindl
z
Hi, community, will make a presentation today about KotlinDL visiting virtually Budapest https://www.meetup.com/Kotlin-Budapest/events/275722879/ Hope to share video after that
m
@zaleslaw Thank you for your presentation yesterday. I liked the way you have shared your passion for data science and Kotlin. What confused me a little bit were statements regarding roadmap and general limitations(Android). For example lower priority for edge computing (Android) or clear plan/idea about coexistence with other libraries in Kotlin data science ecosystem(also non JB). Also I am also missing the main use case for the KotlinDL other than having beautiful DSL and being Kotlin(which is already enough for me 😉 But anyway, keep going and I am looking forward to see a new features and stuff coming ... 👍
z
Thanks for joining, (I was happy to see your question) and feedback @Michal Harakal. Agree about missed use-cases. Could you please write more about lower priority for Android, why it's important and about coexistense with other libraries, please share here, or in separate doc or we could arrange a call to discuss. It will be very helpful.
m
I have answer to the Android part now. I have mobile, especially Android development as background, so maybe be I am biased a little bit. But generally, I consider edge ML(including mobile), very interesting from various perspectives. As user/consumer enjoy AI/ML applications without compromising his/her privacy by doing inference, even additional transfer learning on local device, without cloud. Also low latency makes it a nice user experience (I was getting 3 FPS on live camera stream with an older Android without GPU acceleration with Tensorflow Lite on PoseNet). Mobile SoC having dedicated "neural engines" (like Apple Ax or M1 processors, or considerable effort by Si-Five with Chris Lattner) are for me a strong signal for an demand. Other is also an engineering perspective, where you can have an advantage using light Kotlin based stack instead of general purpose heavy weight frameworks. Also speaking of edge, imagine embedded devices with smaller chips. JB having Kotlin Native, powerful compiler with plugins...
z
Thanks for this answer, @Michal Harakal I'll share it with team, it's very interesting point of view