meh*_*rov 6 python gcc arm dlib google-coral
我正在努力在Google Coral开发板上为Python 安装最新版本的dlib(http://dlib.net/,v19.17)。它与Raspberry Pi 3 B +(似乎具有完全相同的CPU和RAM数量)一起很好地工作,但是在珊瑚开发板上的卡住率为80%(在编译vector.cpp时)。运行跑步时会发生这种情况:
python3 setup.py install
Run Code Online (Sandbox Code Playgroud)
我尝试在Mendel Linux(运行开发板)上进行以下跟踪,但未成功:
我看到的RPI和Coral / Mendel之间的主要区别是孟德尔上的cmake和gcc的旧版本。
我已经将cmake升级到最新版本,但没有成功,但是还没有涉及gcc。
您添加了多少交换空间?我在 /swapfile 中添加了 1GB,它已完成构建。
creating build/bdist.linux-aarch64
creating build/bdist.linux-aarch64/egg
copying build/lib.linux-aarch64-3.5/dlib.cpython-35m-aarch64-linux-gnu.so -> build/bdist.linux-aarch64/egg
creating stub loader for dlib.cpython-35m-aarch64-linux-gnu.so
byte-compiling build/bdist.linux-aarch64/egg/dlib.py to dlib.cpython-35.pyc
creating build/bdist.linux-aarch64/egg/EGG-INFO
copying dlib.egg-info/PKG-INFO -> build/bdist.linux-aarch64/egg/EGG-INFO
copying dlib.egg-info/SOURCES.txt -> build/bdist.linux-aarch64/egg/EGG-INFO
copying dlib.egg-info/dependency_links.txt -> build/bdist.linux-aarch64/egg/EGG-INFO
copying dlib.egg-info/not-zip-safe -> build/bdist.linux-aarch64/egg/EGG-INFO
copying dlib.egg-info/top_level.txt -> build/bdist.linux-aarch64/egg/EGG-INFO
writing build/bdist.linux-aarch64/egg/EGG-INFO/native_libs.txt
creating dist
creating 'dist/dlib-19.18.0-py3.5-linux-aarch64.egg' and adding 'build/bdist.linux-aarch64/egg' to it
removing 'build/bdist.linux-aarch64/egg' (and everything under it)
Processing dlib-19.18.0-py3.5-linux-aarch64.egg
creating /usr/local/lib/python3.5/dist-packages/dlib-19.18.0-py3.5-linux-aarch64.egg
Extracting dlib-19.18.0-py3.5-linux-aarch64.egg to /usr/local/lib/python3.5/dist-packages
Adding dlib 19.18.0 to easy-install.pth file
Installed /usr/local/lib/python3.5/dist-packages/dlib-19.18.0-py3.5-linux-aarch64.egg
Processing dependencies for dlib==19.18.0
Finished processing dependencies for dlib==19.18.0
mendel@arid-valet:~ % python3 -c 'print(__import__("dlib").__version__)'
19.18.0
Run Code Online (Sandbox Code Playgroud)
尽管我不确定您是否能充分利用 dlib 开发板的优势。由于开发板快速推理的主要优势是 TPU,因此您最好使用 tflite_runtime API 或提供的引擎来运行推理。