Franco Marchesoni

Results 8 comments of Franco Marchesoni

Awesome! With my research group we are getting into NILM and probably implement some simulations. What's the state-of-the-art? Last comment is from 2016... Is there an implementation?

The way to reduce the training loss is to provide diverse outputs because you take a min. If you didn't provide diverse outputs then you are in the case with...

You should modify the code of the unsupervised segmentator

There is a paper accompanying the repository. The models are the same except for neural network size, B stands for "base" and is the smallest, L is "large" and H...

To segment an object you should do a click. The unsupervised segmentator uses clicks in a grid and then post-processes the outputs. One thing you could do is to use...

Could you reproduce any of the paper's results?