Closed TheaperDeng closed 3 months ago
@tingwl0122 This PR is kind of "ugly", please also have a look.
Works well for MNIST+MLP noisy label detection
[(0, 0), (100, 58), (200, 93), (300, 103), (400, 105), (500, 109), (600, 109), (700, 109), (800, 110), (900, 110)]
Checked Data Sample Found flipped Sample
--------------------------------------------------
0 0
100 58
200 93
300 103
400 105
500 109
600 109
700 109
800 110
900 110
Works well for MNIST+MLP noisy label detection
[(0, 0), (100, 58), (200, 93), (300, 103), (400, 105), (500, 109), (600, 109), (700, 109), (800, 110), (900, 110)] Checked Data Sample Found flipped Sample -------------------------------------------------- 0 0 100 58 200 93 300 103 400 105 500 109 600 109 700 109 800 110 900 110
Do you have a chance to do it in a larger setting?
Description
1. Motivation and Context
This PR is to add LiSSA as one of the ihvp solver in IFAttributor.
2. Summary of the change
"lissa"
as one of the ihvp solver choice in IFAttributor.collate_fn
parameter for ihvp_lissa and ihvp_lissa_at_x for nested input (in case the input is not tensor)3. What tests have been added/updated for the change?