search

terryky / tflite_gles_app

GPU accelerated deep learning inference applications for RaspberryPi / JetsonNano / Linux PC using TensorflowLite GPUDelegate / TensorRT
MIT License
488 stars 130 forks source link

Bazel build error on Jetson Nano #6

Open JackieYelich opened 4 years ago

JackieYelich commented 4 years ago

I followed your install step "2.2. Build for aarch64 Linux (Jetson Nano, Raspberry Pi)" but this error occurred how can i fix it?

tony@Mediapipe-JetsonNano:~$ chmod 755 bazel-3.1.0-installer-linux-x86_64.sh tony@Mediapipe-JetsonNano:~$ sudo ./bazel-3.1.0-installer-linux-x86_64.sh [sudo] password for tony: Bazel installer

Bazel is bundled with software licensed under the GPLv2 with Classpath exception. You can find the sources next to the installer on our release page: https://github.com/bazelbuild/bazel/releases

#

Build information

Bazel is now installed!

Make sure you have "/usr/local/bin" in your path. You can also activate bash completion by adding the following line to your ~/.bashrc: source /usr/local/lib/bazel/bin/bazel-complete.bash

See http://bazel.build/docs/getting-started.html to start a new project! tony@Mediapipe-JetsonNano:~$ ^C tony@Mediapipe-JetsonNano:~$ source /usr/local/lib/bazel/bin/bazel-complete.bash tony@Mediapipe-JetsonNano:~$ source ~/.bashrc tony@Mediapipe-JetsonNano:~$ sudo nano ~/.bashrc tony@Mediapipe-JetsonNano:~$ source ~/.bashrc tony@Mediapipe-JetsonNano:~$ cd ~/work tony@Mediapipe-JetsonNano:~/work$ ./tflite_gles_app/tools/scripts/tf2.3/build_libtflite_r2.3_aarch64.sh fatal: destination path '/home/tony/work/tensorflow_r2.3' already exists and is not an empty directory. tony@Mediapipe-JetsonNano:~/work$ ./tflite_gles_app/tools/scripts/tf2.3/build_libtflite_r2.3_aarch64.sh Already on 'r2.3' Your branch is up to date with 'origin/r2.3'. /usr/local/bin/bazel: line 163: /usr/local/lib/bazel/bin/bazel-real: cannot execute binary file: Exec format error ERROR: The project you're trying to build requires Bazel 3.1.0 (specified in /home/tony/work/tensorflow_r2.3/.bazelversion), but it wasn't found in /usr/local/lib/bazel/bin.

Bazel binaries for all official releases can be downloaded from here: https://github.com/bazelbuild/bazel/releases

Please put the downloaded Bazel binary into this location: /usr/local/lib/bazel/bin/bazel-3.1.0-linux-aarch64

JackieYelich commented 4 years ago

Did Jetson nano use "bazel-3.1.0-installer-linux-x86_64.sh"? but Jetson nano is aarch64 Linux architecture

terryky commented 4 years ago

At first, 2.2.1. build TensorFlow Lite library on Host PC. And then, 2.2.2. copy Tensorflow Lite libraries to target Jetson / Raspi.

JackieYelich commented 4 years ago

Thank you, I implemented successful. By the way, could this repository implement on Win10?

jiafeng-1 commented 3 years ago

Hey, I have the same problem as you.How did you solve it？

baixianger commented 3 years ago

Thank you, I implemented successful. By the way, could this repository implement on Win10?

Hi, I have met many issues when building the library on Jetson. so may you share the file you had build on the Jetson Nano.(libtensorflowlite_gpu_delegate.so&libtensorflowlite.so).

best regards, Xiang Bai

jk78346 commented 2 years ago

At first, 2.2.1. build TensorFlow Lite library on Host PC. And then, 2.2.2. copy Tensorflow Lite libraries to target Jetson / Raspi.

What is the exact path? I cannot find /home/jetson/lib as mentioned in document, thanks.