Low validation mIoU despite high validation accuracy on part seg

[mackenzie-warren]

I am getting the same error as mention in a previous issue: #34

On the part segmentation, the validation mIoU is only reaching 0.16, although the validation accuracy is about 90%. The was run with the default parameters in the code and using the prepared version of ShapeNet found here: https://drive.google.com/open?id=184MbflF_RbDX9MyML3hid7OxsYJ8oQQ7

I've attached a plot that shows the train and validation losses and accuracy, and the validation mIoU, at every epoch during training.

[mackenzie-warren]

Fix suggested in pull request #38: in calculation of IoU, the tensors need to be converted to int from boolean before adding. E.g. lines 155 in losses.py should be:

intersection = (gt.int() + predict.int()) == 2 union = (gt.int() + predict.int()) >= 1