Live data from Hacker News

Semantic Image Segmentation with DeepLab in Tensorflow

research.googleblog.com

11–12 of 12 posts

Re: Semantic Image Segmentation with DeepLab in Tensorflow

#11
post #7

Is this fast enough to be used as a background removal in live streams?

Not at the kind of resolution you'd want to be using on, e.g., Twitch. In that setting, you could just use chromakey, though? That's '70s technology, cheap and very reliable.

You could but it's cumbersome, amateur streamers might not wish to invest in the setup

Re: Semantic Image Segmentation with DeepLab in Tensorflow

#12

Earlier quoted context omitted.

Yes for Mask-RCNN. For FCN, there is R-FCN. Overall I'm really happy to work in a domain where people share their code and models in such an open way. I take issue with detectron in particular though, because a company the size of facebook in the year of 2018 has no excuse to publish a major software package in python 2. The oldest models they implement are from 2015 (excluding VGG16 which is so prolific it's availab…

The team behind Detectron have published an enormous amount of really good research, but the Detectron codebase struck me as "good research code" rather than something you'd ideally want in production.

Of course, I'm not criticising the fact that they publish those models, nor the models themselves. But even publishing arguably polished python2 code in 2018 is something I take issue with if it's not a legacy code base
Post reply on HN