You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
For example, when treevalue is used in DI-treetensor, some tensors may have the same shape (all dimensions are the same) and partly-same shape (e.g. 1st dimension is the same).
Maybe a constraint should be provided, to simplify the result, such as
fromtreevalueimportTreeValueimporttorcht=TreeValue({'a': torch.randn(2, 3), 'b': {'x': torch.randn(2, 4)}})
t.shape[0] # should be a tree in current treevalue# define some constraintt.shape[0] # should be 2 after defining
The text was updated successfully, but these errors were encountered:
For example, when
treevalue
is used inDI-treetensor
, some tensors may have the same shape (all dimensions are the same) and partly-same shape (e.g. 1st dimension is the same).Maybe a constraint should be provided, to simplify the result, such as
The text was updated successfully, but these errors were encountered: