test1230-lab

Usage

1

Could this work on a dir of unlabeled faces?

Are these all ground truth masks? It seem to include obstructions like hands in the mask area.

General questions

2

What does 128/256 mean for the LSTM? How does this effect the results? What is the optimal rnn layers and batch size? What does word level do?

How do I add another face category?

Could this trained on images instead of tf record format?