Developer preview of TensorFlow Lite
developers.googleblog.com
Developer preview of TensorFlow Lite
1–10 of 80 posts
Re: Developer preview of TensorFlow Lite
#2TensorFlow Lite is TensorFlow’s lightweight solution for mobile and embedded devices! TensorFlow has always run on many platforms, from racks of servers to tiny devices, but as the adoption of machine learning models has grown over the last few years, so has the need to deploy them on mobile and embedded devices. TensorFlow Lite enables low-latency inference of on-device machine learning models.
Looking forward to your feedback as you try it out.
Re: Developer preview of TensorFlow Lite
#3TensorFlow Lite is TensorFlow’s lightweight solution for mobile and embedded devices! TensorFlow has always run on many platforms, from racks of servers to tiny devices, but as the adoption of machine learning models has grown over the last few years, so has the need to deploy them on mobile and embedded devices. TensorFlow Lite enables low-latency inference of on-device machine learning models. Looking forward to yo…
What tradeoffs did you make compared to the original?
Re: Developer preview of TensorFlow Lite
#4TensorFlow Lite is TensorFlow’s lightweight solution for mobile and embedded devices! TensorFlow has always run on many platforms, from racks of servers to tiny devices, but as the adoption of machine learning models has grown over the last few years, so has the need to deploy them on mobile and embedded devices. TensorFlow Lite enables low-latency inference of on-device machine learning models. Looking forward to yo…
What tradeoffs did you make compared to the original?
Using FlatBuffers, for one?
Re: Developer preview of TensorFlow Lite
#5Didnt they announce this at Google I/O? Where it was supposed to be available that day
Re: Developer preview of TensorFlow Lite
#6TensorFlow Lite is TensorFlow’s lightweight solution for mobile and embedded devices! TensorFlow has always run on many platforms, from racks of servers to tiny devices, but as the adoption of machine learning models has grown over the last few years, so has the need to deploy them on mobile and embedded devices. TensorFlow Lite enables low-latency inference of on-device machine learning models. Looking forward to yo…
What tradeoffs did you make compared to the original?
A few tradeoffs we had to make:
- As mentioned below - flatbuffers makes the startup time faster while trading off some flexibility
- Smaller code size means trading off dependency on some libraries and broader support vs writing more things from scratch more focused on the user cases people care about
Re: Developer preview of TensorFlow Lite
#7Is it possible that a future version may be able to leverage CoreML on iOS?
Re: Developer preview of TensorFlow Lite
#8It's spelled "light" - you'd think google could hire an editor.
Re: Developer preview of TensorFlow Lite
#9Is this the next iteration of TensorFlow for Mobile? Is on-device training something planned for the future?
Re: Developer preview of TensorFlow Lite
#10TensorFlow Lite is TensorFlow’s lightweight solution for mobile and embedded devices! TensorFlow has always run on many platforms, from racks of servers to tiny devices, but as the adoption of machine learning models has grown over the last few years, so has the need to deploy them on mobile and embedded devices. TensorFlow Lite enables low-latency inference of on-device machine learning models. Looking forward to yo…
Woah this is cool. I’ve been waiting for this since you announced it. I was thinking about benchmarking it against other solutions . What do you think about other similar frameworks like coreml ?