Tensorflow example not working on nRF Connect SDK

[kclauah]

I have tried tensorflow example on nRF Connect SDK v1.6.1, v1.7.0 and v1.7.1 but all of them are not working.

To reproduce the behavior, build any example under zephyr\sample\modules\tensorflow

Here is the error from output console:

1> Compiling ‘model.cc’
2> Compiling ‘output_handler.cc’
4> ../src/main_functions.cc:19:10: fatal error: tensorflow/lite/micro/all_ops_resolver.h: No such file or directory
4> compilation terminated.
2> In file included from ../src/output_handler.cc:17:
2> ../src/output_handler.h:20:10: fatal error: tensorflow/lite/c/common.h: No such file or directory
2> compilation terminated.
Build failed

[Simon]

Yes, of course, that would be the solution, adding TensorFlow to name-allowlist. I'm sorry for not informing you about this earlier. I tried to add TensorFlow to https://github.com/nrfconnect/sdk-nrf/blob/v1.8.0-rc1/west.yml#L18 and https://github.com/nrfconnect/sdk-nrf/blob/v1.8.0-rc1/west.yml#L96, which I wasn't able to get to work for some reason.

I do not think this is a bug, but rather an active decision by our developers to not include it in the name-allowlist. We do have better support for Edge Impulse samples in the nRF Connect SDK. Check out our Edge Impulse samples here: https://developer.nordicsemi.com/nRF_Connect_SDK/doc/latest/nrf/samples/edge_impulse/data_forwarder/README.html 

Best regards,

Simon

[kclauah]

So what is the reason of not including tensorflow in the name-allowlist? Edge Impulse is also a machine learning framework but why it does not need the tensorflow lite framework?

[Simon]

I talked to a developer about this. He informed me that the Edge Impulse (EI) actually uses TensorFlow and it's even stated on their main page (https://www.edgeimpulse.com/)

The EON compiler ued by Edge Impulse is even better than TensorFlow Lite (it's more optimized for embedded systems).

Also, you could use TensorFlow's Keras APIs to edit the ML model in EI studio.

If you want to learn more, take a look at this: https://blog.tensorflow.org/2021/06/how-tensorflow-helps-edge-impulse-make-ml-accessible.html

[kclauah]

Sorry. I am not familiar with Edge Impulse.

I misunderstand because the Edge Impulse example KConfig does not include tensorflow lite library. And it can be successfully build and run. So I assume they have their own implementation of ML framework.

Even EON compiler is more optimized than tensorflow lite, I do not think it is reasonable to disable tensorflow. At least, developer has an option to use it or not, right?

Thank you for your patience.

[Ivan Angelov]

I do not think Nordic have fixed this issue.
I asked for help at tflite-micro repo, see https://github.com/zephyrproject-rtos/zephyr/discussions/52302

I have my own Zephyr project with my own board based on nRF5340. I am using Zephyr v3.2.99-ncs2, nrf-sdk is v2.3.0.
I modified NRF west.yml as suggested in tflite-micro repo:

diff --git a/west.yml b/west.yml
index a93676a6..5b16929e 100644
--- a/west.yml
+++ b/west.yml
@@ -66,6 +66,7 @@ manifest:
         #
         # Please keep this list sorted alphabetically.
         name-allowlist:
+          - tflite-micro
           - TraceRecorderSource
           - canopennode
           - chre

I ran west update but I get no luck with adding CONFIG_TENSORFLOW_LITE_MICRO=y to my project.
When I ran west -v update I noticed following line:

west.manifest: project tflite-micro in file None ignored: an importing manifest blocked or did not allow it

In my project west.yml I have added tflite-micro project:

    - name: tflite-micro

      path: zephyr/modules/tflite-micro

      url: github.com/.../tflite-micro.git

      revision: 8913f033772ac7009b6d8a1c8817e2399d22d803

After west update I can see the sources of tflite-micro located in zephyr repo:

<>/zephyr/modules/tflite-micro
./
../
.bazelrc*
.clang-format*
.editorconfig*
.git/
.github/
.gitignore*
AUTHORS*
BUILD*
CMakeLists.txt*
CODEOWNERS*
CONTRIBUTING.md*
Kconfig*
LICENSE*
README.md*
SECURITY.md*
WORKSPACE*
ci/
data/
docs/
python/
tensorflow/
third_party/

However, I still could not set

CONFIG_TENSORFLOW_LITE_MICRO=y

Are you able to give some tips?