tensorflow-micropython-examples
tensorflow-micropython-examples copied to clipboard
mocleiri
A custom micropython firmware integrating tensorflow lite for microcontrollers and ulab to implement the tensorflow micro examples.
Hi, I am using ESP32-WROVER-IE board with ESP32-MICROLITE-SPIRAM firmware flashed on it. I am trying to test the person detection model but it does not work. Based on results, predictions...
There was a request for Zephyr support: https://groups.google.com/a/tensorflow.org/g/micro/c/Uun_ZSkv2OQ Litex VexRiscv SoC Arty FPGA But I'm also interested to see if this can be a way to get STM32 working.
Recently tflite made a new example implemented using tflite python on raspberry pi. https://github.com/tensorflow/examples/tree/master/lite/examples/object_detection/raspberry_pi https://youtu.be/mNjXEybFn98 The tflite model size is 4MB so can be tried on Teensy 4.1 or other...
Hello @mocleiri, Thanks for the fantastic work. Could you please guide me on how to port tensorflow-micropython-example for both SAMD boards([Wio Terminal](https://wiki.seeedstudio.com/Wio-Terminal-Getting-Started/) and [Xiao](https://wiki.seeedstudio.com/Seeeduino-XIAO/))? Here is [Ardupy](https://github.com/Seeed-Studio/ArduPy/tree/master/ports/samd/boards) which is supported...
I am trying to run the Hello World example with ESP32. The values are printed but afterwards the following issue is shown: "PROBLEM IN THONNY'S BACK-END: Exception while handling 'get_globals'...
I'm splitting this question from surajkumarpandey in #99 out into a separate issue. ` Is there a documentation for the functions/objects used in the Hello_world example? I am trying to...
Hi I was wondering if it is possible to customise audio frontend to allow for different sample rates, stride size's and duration size's. Also is audio frontend faster than [ulab's...
On June 3, 2022 https://github.com/tensorflow/tflite-micro/pull/1147 was merged into the upstream tflm repository. It added a C Python wrapper for running tflm in unix. As part of this it also added...
This would allow for more accurate memory allocation in the case the developer wants to re load the neural network in but keep the same section of memory for the...