Bro ham log direct assembly main Kartain Hain and give even less functionality 
This startup offers a way to convert Keras models to pure C for deployment in embedded systems. Sounds quite useful (but only supports a fairly narrow subset of functionality) https://www.aitransformer.com/
-
-
This Tweet is unavailable.
-
-
-
-
Will eventually compile all deep learning models to all embedded devices using https://GitHub.com/ai-techsystems/dnnCompiler …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Could you send us more feedback on how we can improve this? Really appreciate your gesture. Thanks.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
And how does improved speed/efficiency compare with a spiking transformation? Or just using
#JuliaLang ?Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Sounds like a valuable thing to build but “upload your code and this black box will compile/transpile it” is not gonna be popular with devs
-
Surely this will be moot with Swift?
End of conversation
New conversation -
-
-
hm, interesting
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This is interesting, but it means you end up with a bunch of platform-specific versions of your model that you may have also hand-optimized and will find it difficult to update in the future. We take a different approach with TensorFlow Lite: https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/experimental/micro/README.md …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.