Hacker News new | past | comments | ask | show | jobs | submit login

For image data, Caffe (http://caffe.berkeleyvision.org/) is dominant (most deep learning computer vision research I see is done with Caffe). However, that's the chief problem with Caffe - it's very difficult to extend because it revolves so much around "just specify attributes" and train.

Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | Legal | Apply to YC | Contact