Download and install scipy and numpy+mkl (must be mkl version) packages from this link (all credits goes to Christoph Gohlke). Pip install dlib and then pip install face_recognition. Just install dlib and face_recognition (not always on the newest version): (I've included the compiling procedure of Boost in this tutorial) Also, you can use precompiled binaries for specific MSVC you have, but I don't suggest. ( ONLY FOR older versions of dlib) Boost library version 1.63 or newer. CMake for windows and add it to your system environment variables. Of course Python3 (I used Python3.5 圆4 but the other versions may work too). (Visual C++ 2015 Build Tools didn't work for me, and I got into problems in compiling dlib) Microsoft Visual Studio 2015 (or newer) with C/C++ Compiler installed. (I've used this tutorial with these tools installed on Windows 10, but the newer versions may work too.) Remember that you still need to meet the following requirements. The new version of dlib doesn't need Boost anymore, so you can skip it. But I haven't seen any difference between these two in other subjects. In my tests, the performance of this tool in Windows 10 was about a quarter compared to Ubuntu, built with the same specs. 
IMPORTANT: Actually, this project has been done for Linux systems, especially dlib. It may be useful for some people to try to use this tool on a Windows machine. I've successfully installed and tested this tool on my Windows 10 machine, and I'm writing a simple procedure to install it.
0 kommentar(er)
