compute-engine: Error while performing benchmarking

Hello all, I am having raspberry pi 3b+ installed with 32bit raspbian os when I try to do benchmarking from the documentation https://docs.larq.dev/compute-engine/benchmark/ I am getting the following error as shown in the picture.

pi@pi:~/Desktop $ chmod +x lce_benchmark_model
pi@pi:~/Desktop $ ./lce_benchmark_model --graph=quicknet.tflite --num_threads=4
./lce_benchmark_model: /lib/arm-linux-gnueabihf/libm.so.6: version `GLIBC_2.29' not found (required by ./lce_benchmark_model)
./lce_benchmark_model: /lib/arm-linux-gnueabihf/libc.so.6: version `GLIBC_2.33' not found (required by ./lce_benchmark_model)
./lce_benchmark_model: /lib/arm-linux-gnueabihf/libc.so.6: version `GLIBC_2.32' not found (required by ./lce_benchmark_model)
./lce_benchmark_model: /lib/arm-linux-gnueabihf/libc.so.6: version `GLIBC_2.34' not found (required by ./lce_benchmark_model)
./lce_benchmark_model: /usr/lib/arm-linux-gnueabihf/libstdc++.so.6: version `GLIBCXX_3.4.29' not found (required by ./lce_benchmark_model)
./lce_benchmark_model: /usr/lib/arm-linux-gnueabihf/libstdc++.so.6: version `GLIBCXX_3.4.26' not found (required by ./lce_benchmark_model)
pi@pi:~/Desktop $

ldd --version gives ldd (Debian GLIBC 2.28-10)2.28

Also the process for performing inference on raspberry pi is not so clear for me. I trained my own model using larq library, converted the model to tflite format as given in end to end guide https://docs.larq.dev/compute-engine/end_to_end/, but after generating the tflite , I am struck what to do, how to perform inference using this tflite file on raspberry pi. I was looking at building models for arm https://docs.larq.dev/compute-engine/build/arm/ , but I am not able to perform inference. Can anyone please guide me how to perform inference on raspberry pi board and please help in resolving the issue. Thank you in advance.

About this issue

Original URL
State: closed
Created a year ago
Comments: 44 (1 by maintainers)

Most upvoted comments

Thanks @Tombana It is working with Manjaro OS, Finally BNN inference is done on RPI using LCE. Really appreciate your continuous help and patience.

sandeep1404 on Apr 26, 2023

Hi @Tombana, sorry I removed “convert_saved_model” from this line but did not remove convert_keras_model , I commented on the above lines and rebuild it, Now I can able to install and import the lce. I will try to load the interpreter and run the inference if I will face any issues I will post them here, I really appreciate your patience in replying to all my queries back, Thank you for the help.

sandeep1404 on Apr 26, 2023

@sandeep1404 It seems like the strip utility does not accept aarch64 libraries. Can you comment-out the strip command from the build_pip_package.sh script, and then try to run it again? Once that’s successful, a .whl file should appear in the folder artifacts. You can copy that .whl file to your raspberry pi and then just use pip install ./filename.whl on it.

Hi there, I have the same problem with the Raspberry Pi OS Lite (64-bit), which was released on 2023-02-21. Is there any suggestion for which OS I should use?

Hi @bywmm, I recommend Manjaro Linux (easy setup) or Arch Linux (for more advanced users) for Raspberry Pi. These distributions usually come with the newest packages.

Tombana on Apr 26, 2023