Closed justin-hpcnt closed 4 years ago
Thanks for pointing out! I found that this might be a problem for PyTorch versions higher than 1.2.0. For PyTorch versions 1.1.0 and lower, the logical operations return ByteTensor. After 1.2.0, BoolTensor is introduced so the logical operations return BoolTensor. In short, use ByteTensor for Pytorch 1.1.0 and lower, and BoolTensor for PyTorch higher than 1.2.0.
When running
./test_coco.sh
, below error occurs.It can be simply resolved by changing
edge = self.ByteTensor(t.size()).zero_()
toedge = self.ByteTensor(t.size()).zero_().bool()
at https://github.com/xh-liu/CC-FPSE/blob/master/models/pix2pix_model.py#L216