Add ImageNet to Benchmarks

[vlomonaco]

Add ImageNet as a benchmark based on the Pytorch data loader.

[vlomonaco]

You can check here how it is commonly used: https://continualai.discourse.group/t/cl-papers-with-experiments-on-imagenet/65/2

[PatrickZH]

Thank you for providing this. The pull request that I just submitted is incremental-batch learning or incremental-class learning in the papers like iCaRL - CVPR-2017 and EEIL - ECCV-2018.
The current code is compatible with different class numbers in a batch. However, the initialization function (with part of classes) hasn't been included in the code. I will add this function soon.

[vlomonaco]

@PatrickZH can we close this issue or are you still working on it?

[PatrickZH]

Hi Vincenzo, I will submit the final pull request on this Wednesday. Then we can close it. Thanks! Best regards, Bo Zhao

…

On Mon, May 25, 2020 at 1:48 PM Vincenzo Lomonaco ***@***.***> wrote: @PatrickZH <https://github.com/PatrickZH> can we close this issue or are you still working on it? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <https://github.com/vlomonaco/avalanche/issues/1#issuecomment-633556081>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ACNYTMW3VO6RFBN73YRVIILRTJSLXANCNFSM4MFPQ23A> .