Open linwei0763 opened 1 year ago
Hi, thank you for your work.
I am reading your code while there seems to be a mistake.
model.py line 100 return torch.cat(( self.mlp(concat), features.expand(B, -1, N, K) ), dim=-3)
features.expand(B, -1, N, K) the features should query neighbours instead of simply duplicate the values.
Hi, thank you for your work.
I am reading your code while there seems to be a mistake.
model.py line 100 return torch.cat(( self.mlp(concat), features.expand(B, -1, N, K) ), dim=-3)
features.expand(B, -1, N, K) the features should query neighbours instead of simply duplicate the values.