Hacker News Reader

does it mean PyTorch or Tensorflow are better for research, experimentation and Caffe2 was more designed for production?

Or it actually means Caffe2 was designed for both research and production

View on HN

PyTorch definitely makes experimentation much better. For example, if you want to train some system that is highly dynamic (reinforcement learning, for example), you might want to use a real scripting language which is Python, and PyTorch makes that really sweet.

Sometimes the line gets a bit blurred - for research that are focusing on relatively fixed patterns, such as Mask RCNN, both PyTorch and caffe2 are working great. In fact, Mask RCNN is trained in Caffe2, and that also makes things much easy when we put it on mobile - what our CTO Mike Schroepfer showed in his keynote is a Mask RCNN model trained and then deployed onto mobile with Caffe2.

When are you planning to release the Mask-RCNN code?

I'm trying to implement the RoIAlign layer in Tensorflow and I've a few doubts and having the author's code would definitely help in implementing it.

Reply on news.ycombinator.com