Add Graph class #403
Add Graph class #403
Conversation
|
@FilippoOlivo I would avoid to write a graph solver, |
FilippoOlivo
force-pushed
the
0.2
branch
10 times, most recently
from
567f207 to
1867274
Compare
dario-coscia
changed the title
FilippoOlivo
force-pushed
the
0.2
branch
5 times, most recently
from
11a43ec to
290641a
Compare
FilippoOlivo
force-pushed
the
0.2
branch
3 times, most recently
from
7ba1b32 to
238f665
Compare
FilippoOlivo
added
pr-to-review
FilippoOlivo
force-pushed
the
0.2
branch
2 times, most recently
from
cf42cf4 to
6e13f96
Compare
| if isinstance(pos, torch.Tensor): | ||
| pos = [pos] | ||
| edge_index = [edge_index] | ||
| distance = [pos_[edge_index_[0]] - pos_[edge_index_[1]] ** 2 for |
There was a problem hiding this comment.
edge_attr is computed as the square of the distance, instead of the standard distance. Is this the desired behavior?
| raise ValueError("The method must be 'radius' or 'knn.") | ||
| if isinstance(pos, (torch.Tensor, LabelTensor)): | ||
| if isinstance(pos, LabelTensor): | ||
| pos = pos.tensor |
There was a problem hiding this comment.
I would keep pos as a LabelTensor to simplify managing coordinates in multidimensional problems. For example, in a 2-dimensional problem, how would you access the x or y coordinates individually? @dario-coscia, can you think of any scenario where accessing coordinates separately might be useful?
|
@FilippoOlivo please remove from commit a862dc8 to f0ddee6, they should pertain to a different PR #433 . Only graph updates should be here |
|
@dario-coscia Done! Remove useless commits |
|
I would say green light on my side! |
|
@FilippoOlivo there is still the
|
dario-coscia
added
pr-to-fix
This PR refers to the issue #400