Become a leader in the IoT community!
New DevHeads get a 320-point leaderboard boost when joining the DevHeads IoT Integration Community. In addition to learning and advising, active community leaders are rewarded with community recognition and free tech stuff. Start your Legendary Collaboration now!
I didn’t use bazel. Since I’m using cube ide, I used this generation script: https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/docs/new_platform_support.md#step-1-build-tflm-static-library-with-reference-kernels
It ouputs a directory that I included in my project and added necessary directories as “includes” folder in build. I still needed to paste further directories from the tflite-micro projects itself as I’m getting error about specific header files being not found when building
But once I successfully integrated it into my project, I’m getting a lot of errors from the tensorflow code itself. So I temporarily kept my project aside for now. I’m away without my laptop now, but I can answer any questions.
I saw that
after adding tflite with X-Cube-AI my project won’t even build
so I left the cubeide
now trying some other `Baaazeeel` way
Have you tried building the examples?
https://github.com/tensorflow/tflite-micro/tree/main/tensorflow/lite/micro/examples/hello_world
I didn’t use X-cube-AI. I tried to just integrate the whole micro directory into my build.
For me, it seems like they want us to follow their own directory tree and build system instead of using it as a library in another project
Ah so Bazel is the way
we can change it most probably but we have to change it quite a lot
I would say most probably I am at the last stage of success
one more error fixed and I am good to go
and such his epitaph read
see my toolchain is now changed
bad news i was unable to handle this include
I tried many ways but sadly it didn’t work
I hope it will work by tomorrow morning
don’t be weary, issues are finite
here how I did it for the stm32f7xx_it.h https://github.com/daleonpz/cmake-template/tree/example/hello_world_stm32f746G_disc/src
here the *.cmake for the toolchain https://github.com/daleonpz/cmake-buildsystem/blob/04d2c37d2d9c83212f4a579c42fdad34b815c2a4/toolchains/cross/cortex-m7_hardfloat.cmake
with cmake we have no issue man
but we have to use bazel
Hmmm @undefined2001 try finding a guide to migrate from cmake to Bazel
maybe https://github.com/bazelembedded/bazel-embedded
@superbike_z , did you try to convert the model to c array
the model is converted its running the inference thats an issue
@undefined2001 I *think* I got it working.
Run `make -f tensorflow/lite/micro/tools/make/Makefile TARGET=cortex_m_generic TARGET_ARCH=cortex-m4+fp microlite` to create a `libtensorflow-microlite.a` library file.
Then add it to your stm project and add it as a library to link in build settings. Include the necessary header files as well.
I just made an inference with their hello world example. I keep getting output 52, which I don’t know is correct or not but atleast it is working.
let me look into it
bazel is killing me man
trying it since last week
non stop everyday
@.araki_ how you have tried to implement in your project
can you please share your github?
I’m not making any actual project at the moment. I’m just learning and wanted to get TFLM working inside an STM generated project. Here’s a gist on steps I followed:
https://gist.github.com/arkreddy21/427a97d4cd1431ebc766dd70b5dc8104
I just solved many errors that happened while tring to make it work. So ask me if there is any specific issue
I am getting error related to flatbuffers
include headers
add core/Inc/third_party/flatbuffers/include to the includes directory in build settings
there is nothing in it
include is empty
I compiled the library
now after that I have to use that i guess in my project
I have a `libtensorflow-microlite.a`
you also have to generate a file structure and copy it to your project, once see my gist
this portion?
yep
I want to use my custom model what should I do?
any idea
This just sets up everything. To run inference, first convert your model into C array. Then you need to invoke it. I added an example main file to the gist, once refer it.
You can also look at the generated examples in /tflm-tree
I did it to an extent but have you used error reporther?
in my case error reporter is misisng
I did not use error reporter but it seems to be present in tflm-tree.
Also, be sure to include all the Operations your model needs in the OpResolver. And allocate enough arena size
my bad
in my case it is also there
just the path was a bit different
let me fix it too
thanks for all the help
I will write a detailed guide since I am not doing it with CubeIDE
@.araki_ here comes the nightmare
Ah, I guess rtos and tflm is too much. You’re doing release build right, What board/mcu are you using?
I have only 128KB ram
I think too much
I wonder what optimization you will employ now
I can make release but that won’t do much
`Os`
Idk about your build system but stm cube gave me 10x less size on release. Also STM32F407 has 128kb ram + additional 64kb core coupled ram, which could be used with some tinkering I think.
I have 128KB ram
using stm32f446re
no extra ram
I am using optimization though
but the issue is with my data sample’s array and also the model
model was approx 58kb
Well, that itself takes half the ram. Maybe you need to retrain smaller network, with quantization and all
also rtos taking some memory itself
Its just 9% over, so I think you could optimize it
well whole firmware is not complete
I haven’t created the task and assigned them stack
I was just trying to do a test compile
Oh. I don’t really know about your project so can’t help much. I don’t have experience with rtos either
yeah but now I am happy atlease I added `tflite-micro` in it
Yeah that’s good. I’m still learning. I’m taking a tinyml course and wanted to use tflite-micro on my board. There’s still a long way before I can make any decent project
same here too
maybe I should move to some nucleo 144 board
that have approximately 1MB+ ram
Yeah, a bigger mcu is best when tinkering. You can focus on functionality first and optimization later
So what is happening, did you minimize enough and get inference running.
nope it seems there is not much to minimize the code I was compiling it was without assigning stack to each task
so there are more code coming
also, I haved enabled the grabage collection of linker
that also didn’t help much
ah so you need to optimize you stack sizes for the tasks? so a freertos issue not a ML issue
no no what I am saying is I haven’t even assigned memory for each task before that it already overflowing
Ah then where is your memory going?
58kb for the model
and the rest to freeRTOS
normal freeRTOS use to consume around 50kb of my ram and the rest increament wasn’t proportional
how much RAM is on the st you are using
128KByte
so your tasks are taking 70kb?
I’m a fool
My stack
NO no I didn’t say that, I am asking it this is indeed the case
I was using default configuration of freeRTOS
and that assigned 75kb for heap
nuance is key
Take a look at this @undefined2001 , just found out about this.
https://blog.st.com/stm32n6/
https://www.mouser.in/ProductDetail/STMicroelectronics/NUCLEO-N657X0-Q?qs=%252BXxaIXUDbq1Ro77qvzSZDA%3D%3D
it’s an interesting MCU but let’s see when we can use it
CONTRIBUTE TO THIS THREAD