czjghost

> Hello author, Thanks for the release of the code of your paper. > > After reading your paper and code, I wonder if the best 'lambda' for EWC ++...

 As far as I can see, there is no problem in reservoir_update.py, the method author has implemented is the batch-level operation for reservoir sampling, not the sample-level operation for...

> Hello, can you provide the link to download the imagenet2014 dataset? https://image-net.org/challenges/LSVRC/2014/2014-downloads.php

I also have problem about the arrangement of ILSVRC2014 in this project, it seems that author maybe use ILSVRC2012 rather than ILSVRC2014 ? update 2023.4.20: By downloading the ILSVRC2012 and...

Hello, I am coming, about the dataset, first, you should download the original [ILSVRC2012](https://image-net.org/challenges/LSVRC/2012/2012-downloads.php), specially, only downloading **Training images (Task 1 & 2)** and **Validation images (all tasks)** are enough:...

> hey, I have also noticed this paper. But I find the experimental results on CIFAR100 of this two paper are the same. aha, let me see. thank you~

I think it is the same as saving torch model, but for the testing samples are not the same among all runs, you should save those sample at the same...