FaceID using customized built postgresql

One of my past projects is based neural network in 2020. The solution is quite simple:

I adopted the model and algrithm from face_recognition, and my team trained on sample faces from our internal system to improve the accuracy to reduce the human involvement and save costs. During development, we found that there is a limit of postgres: CUBE_MAX_DIM, my team customize the build of postgreql to work around the limit. The idea is copied from a postgresql sharing in a meeting. The file is a pdf file, today I can’t find the file. I will update this article sometime later if I find the pdf.

Today I wanted to write my past projects one by one and found the article.