-
The Vehicle Configuration Files (.VCF) references component files for weapons (.GDF). For example `WEPN........goilslck.gdf.` These are parsed by the VcfParser, but they are not used anywhere at the …
-
Thank you for your excellent work! Could you share your code about continual Learning based on GDumb?
-
Thanks for the great works, I would like to ask where can we find the code for task incremental learning applications conducted in your first two papers (SVHN→MNIST→USPS). It seems like the current CL…
-
The insertion process at the selector is a bottleneck. Postgres inserts with 80-100k rows/second, which means waiting for 30+ minutes for a day of Criteo data to be inserted.
For many simple strate…
-
I just find that the temp_batch (composed of several tasks) whose batch size is args.temp_batchsize is iterated args.temp_batchsize times. Would you mind explaining the reason why the arg "iterations"…
-
Hi all, I'm new to Avalanche. I started with the tutorial but a code in the tutorial didn't work. Can some one please help me?
**The code:**
from torch.optim import SGD
from torch.nn import Cros…
-
First of all - thanks for the great codebase!
I do have a quick question. In the GDumb implementation , it seems the optimizer is placed inside of the training loop, which means that the scheduler …
-
For efficiency, i only run strategy ER, GDumb(OOM), SCR.
The ER result can be reproduced as the paper. However, the scr result is unexpected low as listed below.
Are there any hyper-params incorrect…
-
🐛 **Describe the bug**
When I tried to run the example code following https://avalanche.continualai.org/from-zero-to-hero-tutorial/04_training#how-to-write-a-custom-strategy, I encountered an `Attrib…
-
For GDumb strategy, the selector needs to be informed of the data's label along with the key and timestamp.