Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
First, thanks for making your code public. It was very helpful.
I just found very minor error in meta_learn function of lightning_mtl.py.
If "labels" of incoming batch is sampled as
[26., 26., 26., 26., 26., 26., 26., 26., 26., 26.,
0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
15., 15., 15., 15., 15., 15., 15., 15., 15., 15.,
37., 37., 37., 37., 37., 37., 37., 37., 37., 37.,
47., 47., 47., 47., 47., 47., 47., 47., 47., 47.]
new label for multi task learning is changed as
[ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
4, 4, 4, 4, 4, 4, 4, 4, 4, 4]
Because after "26" label(1st row) is changed to new "0" label(1st row),
then "0" labels(both of 1st row, 2nd row) are changed to new "1" label.
So to avoid this less likely situation, I made a labels_new tensor.
Thank you.