Closed tingwl0122 closed 3 months ago
For MNIST, TracIn works well. For CIFAR-2, it is just like random checking. Not sure TracIn functionality yet...
(Update: IF is also similar to this)
For MNIST, TracIn works well. For CIFAR-2, it is just like random checking. Not sure TracIn functionality yet...
(Update: IF is also similar to this)
Hi @TheaperDeng , I think this is also ready to be merged. The only concern is the poor performance of TracIn on CIFAR-2 noisy label test. But since IF also gives similar result, I guess this is normal.
please fix the conflict before merge the PR.
Description
This PR adapts the current
example/mnist_lr/influence_function_noisy_label.py
to TracIn on MNIST/CIFAR-2 .1. Motivation and Context
Test the functionality of TracIn
2. Summary of the change
Subset
for easier usageepoch_num
support to train MNIST3. What tests have been added/updated for the change?