elephantum

I don't understand, why isn't there more excitement about this.

This is huge in my opinion.

Now you can get any environment in container on your local machine, with working Intellisense and all the IDE integrations.

YOLO is a combination of backend encoder and head. Backend (Darknet) is unique to YOLO, that would be the main difference with SSD, if I'm not mistaken.

Interesting idea!

Though I have a question: in order to calculate C you need a way to attribute proposal and ground truth. It's trivial in case when there's only one instance of each class in the image.

But how does it work, when you're working with a set of same-class object? For example detecting each car in traffic.

There’s a project that compiles ONNX models: https://onnc.ai

Like Tensor Processing Units?

It means you have two extra special cases: 1) list is empty; 2) left edge is the right edge (I.e. length is 1)

It's amusing, that you can substitute every reference from Ruby to Python and Rails to Django and article would still make sense.

Except for the part about running in production. Seems like Python is a bit ahead there.

Is it possible that they foresee problems with Amazon valuation and this a way to save half of the assets they have?

Whether it's true will depend on what his wife is about to do with the shares.

That's the offroad car I've been dreaming about!