解析face-recognition-opencv开源项目 FROM pyimagesearch

原文章地址：https://www.pyimagesearch.com/2018/06/18/face-recognition-with-opencv-python-and-deep-learning/ （含代码）

注：只解析图片识别，视频识别暂不解析

we are not actually training a network here — the network has already been trained to create 128-d embeddings on a dataset of ~3 million images.

此项目不训练神经网络，神经网络已经被训练好并被打包了

Then, during classification, we can use a simple k-NN model + votes to make the final face classification. Other traditional machine learning models can be used here as well.

此项目分类人脸的时候使用k-NN（k最近邻）算法来分类不同人脸，也可以换其他分类算法来分类

python-argparse-command-line-arguments解析：https://www.pyimagesearch.com/2018/03/12/python-argparse-command-line-arguments/ 此技术可以用python代码来实现定义命令行语句，相当于在命令行调用相应功能

 Linux pwd命令用于显示工作目录。 执行pwd指令可立刻得知您目前所在的工作目录的绝对路径名称。

收集要识别人脸数据集的三种方式：1.摄像头获取 2.Bing Image Search API来编程获取 3.手动获取 https://www.pyimagesearch.com/2018/06/11/how-to-build-a-custom-face-recognition-dataset/

 

报错：RuntimeError: Error while calling cudaMalloc(&data, n) in file ... code: 2, reason: out of memory

参考我另外一篇博客：https://blog.csdn.net/zoukai1587/article/details/88977357

 

待更......