payne53

> Yes it is correct. To quickly share the weights I just trained for 2K iterations. The full training cycle is 10K. Dear @bardiadoosti , Thanks for posting the GraphUnet...

I got 0.363 map, but I use the semantic_label released by the author.

> @payne53 Thank you so much for pointing it. Could you reproduce the performance on QuickDraw dataset? Sorry, I haven't tried QuickDraw yet.

The external vlfeat is not compiled.