Siraj Raval covers PyTorch very well in a 5 min video (https://youtu.be/nbJ-2G2GXL0).

It comes down to design decisions, of which I'm not qualified to go into. This article made the front page last week, about the downsides to Tensorflow which people rarely talk about: http://nicodjimenez.github.io/2017/10/08/tensorflow.html

And this interview with a Tensorflow engineer (10 mins) explains a little bit about those design decisions (https://youtu.be/axRHotkkTVI).

I guess whatever qualities both platforms have does not really matter compared to how much traction they get. If the world converges to one platform, then you should probably go with that platform, no matter how good the other platform is. The reason is that things are just moving too fast, and you don't want to spend your time porting new research from one platform to the other.

That said, I'm curious why PyTorch (or specifically Autograd) couldn't have been built on top of TF.

I would roughly classify them based on use cases:

* If you are working on research such as optimization or other improvements on the algorithms of training neural networks, PyTorch is a better option as it is (in my experience) much more understandable and easily modified.

* If you are experimenting with network architectures and aren't going to be mucking around with the internals (e.g., developing a new optimization algorithm), Tensorflow is a better option.