How we load a #TensorFlow Lite Model ... Before running inferences
How we run inferences with a #TensorFlow Lite Model
Missing FlatBuffers when building TensorFlow Lite for #BL602 ... Let's fix this
Fixed the #BL602 Makefile to install FlatBuffers ... For compiling TensorFlow Lite
TensorFlow Lite app exports the functions "setup" and "loop" (So cute!) ... Let's add them to #BL602 Command-Line Interface
Our #BL602 TensorFlow Build has lotsa missing functions ... Let's fix the build
TensorFlow Lite Makefile looks complicated ... Let's download "gemmlowp" the simple way on #BL602
Our #BL602 TensorFlow Build hitting some Math errors ... Let's fix them
#BL602 Makefile for TensorFlow Lite needs this ... To fix the Math build errors
#BL602 TensorFlow Lite also needs the "ruy" library ... For matrix multiplication
Our #BL602 Build of TensorFlow Lite ... Fixing a few more missing C++ Functions
Source Folders for TensorFlow Lite are defined in the #BL602 Makefiles "bouffalo.mk" and "component.mk"
Our #BL602 Build of TensorFlow Lite calls "new" and "delete" to Allocate and Deallocate C++ Objects in Heap Memory ... But it's supposed to use Static Memory, not Heap Memory ... Let's find out why
Setting this flag will tell TensorFlow Lite to use Static Memory (instead of Heap Memory) on #BL602 ... Neat!
Final few Missing Functions for TensorFlow Lite on #BL602 ... Let's find out what they are
Just realised that "CPPFLAGS" works for building #BL602 C++ Libraries, but not for BL602 C++ Apps ... Dang
Aha "CPPFLAGS" should be defined in #BL602 "bouffalo.mk" ... Not "Makefile" 🙄
We disable Thread-Safe Initialisation by setting "-fno-threadsafe-statics" ... This fixes the Missing Functions "__cxa_guard_acquire" and "__cxa_guard_release" in #BL602 TensorFlow
We set the #BL602 Global Destructor "__dso_handle" to null ... Since we're not destroying the Static TensorFlow Variables
How we might teach #BL602 ... To light up the LED 😂
Lupy, does pine cone have enough number crunching power to run bigger ai models? Or do You use tf here just to train models on pc rather than running them?
If youd get me a hw i could do some sw devel for you. Anyway. Youre no longer as responsive as you used to be. Making up my mind about unfollowing. Cheers.
QOTO: Question Others to Teach Ourselves. A STEM-oriented instance.
An inclusive free speech instance.
All cultures and opinions welcome.
Explicit hate speech and harassment strictly forbidden.
We federate with all servers: we don't block any servers.