Re:How I Used Deep Learning to Train a Chatbot to Talk Like Me
by sarabande on Friday August 11, 2017 @04:47AM
(#14987760)
Also, although difficult, Gaussian blurs can be in certain cases reversed (even though this one is so obvious there was no point in blurring the names). I prefer a fat black box when censoring.
BTW: just blurring people's names using a gaussian blur operator is not enough, if your radius is too small. From the screenshots of chats, you can tell names like "Arvind Sankar", "Manu Saravanan", etc.