Our 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

github.com/lupyuen/bl_iot_sdk/

Show thread

We disable Thread-Safe Initialisation by setting "-fno-threadsafe-statics" ... This fixes the Missing Functions "__cxa_guard_acquire" and "__cxa_guard_release" in TensorFlow

github.com/lupyuen/bl_iot_sdk/

Show thread
Follow

Lite runs OK on yay! 🎉 This pre-trained TensorFlow Model is supposed to infer "y = sin(x)" ... Let's verify the output! 🥧

github.com/lupyuen/bl_iot_sdk/

· · Tusky · 1 · 0 · 0
Show more

@Blort So that we can run Machine Learning on BL602 🙂 I'll add more use cases soon

Sign in to participate in the conversation
Qoto Mastodon

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.