128 dimension face matching algo

## Description

(A clear and concise description of what the feature is.)
Generating Face matching 128 dimension

Will this change the current api? How?
As of now embedding returned by the model are of 512 dimension. http://djl.ai/examples/docs/face_recognition.html
how can the embedding be generated with the 128 dimension size.

Who will benefit from this enhancement?
Data generated with 512 dimension is of 2KB which can't meet the storage size such as QR codes.

## References

- list reference and related literature
- list known implementations

https://discuss.tensorflow.org/t/using-the-facenet-model-for-face-recognition-in-android/1409