A better tensorflow implementation of deepinsight, aiming at smoothly production ready for cross-platforms. Currently only with inference, training code later.
I give you three reasons why not use this repository:
It is not easy to run example.py if you are new coder. you must change file path in some code file.
dropout_rate is not reasonable. as generally, we look forward to get same feature vector for inference a image twice, but we will get difference feature vector if you use dropout_rate under 1.
According to my practical experience, distance of my two face images is larger than distance of my face image and other person face image. so, the provided model is not practical.
I give you three reasons why not use this repository: