Andrea Azzini

@DrM175u correct, the network I have implemented is not the canonical segnet. I have implemented the canonical version, but I decided to leave it outside the scope of the project....

Hey @Zumbalamambo, you can refer to https://github.com/andreaazzini/segnet.tf/issues/8.

So, I'm still far from achieving good results on VOC (I had the time to complete only 72 epochs). Some examples (good, promising and bad).    My gut...

@c0nn3r any better results on your side?

@c0nn3r https://github.com/andreaazzini/retinanet.pytorch/blob/328f63e12fdcd9e5b11f8828828b302245b13cf8/demo.py I removed `demo.py` from master because I'm working on an evaluation script, and the demo script needs to be changed accordingly.

@c0nn3r Are you using my encoder or @kuangliu's?