vlomonaco/ar1-pytorch

AR1* with Latent Replay, implemented in PyTorch

ar1-pytorch's Issues

Reproducing results of NI and NC scenarios

Hi @vlomonaco,

Thanks for the great algorithm and codebase!
I was about the reproduce the results of NICv2_391 by following the readme instruction.

I'd like to also run experiments of NI and NC scenarios as shown in this paper. I attempted to modify line 87 directly in ar1star_lat_replay.py but the results (~30 to 40%) I got was worse than NICv2_391 (which I expected to be a harder case).

Could you kindly show us where else needs to be adjusted (lr or other hyperparameters) in order to make it work properly? I think I am missing something. Thanks in advance!

Fu-Jen

Reproducing results for AR1* with 500 latent replay size

Dear Mr. Lomonaco,

Thank you for making the code of AR1* publicly available and re-implement it in pytorch.
I'm trying to recreate the result of Figure 4 of the paper https://arxiv.org/pdf/1912.01100.
The setting is NICv2-391 with replay buffer size 500.

I have kept all the parameter of params.cfg the same and only changed rm_rz from 1500 to 500, the result is an accuracy of 63.62%, specifically: Accuracy: 0.6362827923521566.

This is far from the reported ~70% as shown below.

Is there some parameter I should change to recreate the results from the paper?

Thank you in advance,

Best regards,
Wei

No such file or directory: '/home/admin/ssd_data/core50/paths.pkl

Hello,

Thanks for the code. When I tried to run it, I got this error:

"Traceback (most recent call last):
File "ar1star_lat_replay.py", line 87, in
dataset = CORE50(root='/home/admin/ssd_data/core50', scenario="nicv2_391")
File "/content/ar1-pytorch/data_loader.py", line 94, in init
with open(os.path.join(root, 'paths.pkl'), 'rb') as f:
FileNotFoundError: [Errno 2] No such file or directory: '/home/admin/ssd_data/core50/paths.pkl'

Thanks for helping me solve this issue