-
See feature-request here: https://github.com/ContinualAI/avalanche/discussions/470
-
Current link for the API Doc is `continualai.github.io/avalanche`. I would prefer something like `avalanche-api.continualai.org`!
-
Hi all,
I'm working on implementing Class-Balanced and Experience-balanced Replay (See #479).
I want to provide the opportunity for the user to select a fixed capacity prior or adaptive to all see…
-
Using the replay plugin with `mem_size = 100`, together with the Naive strategy I noticed that when the `MultiTaskMultiBatchDataLoader` wants to reinitialize one of the data loaders (https://github.co…
-
**Describe the bug**
The script provided below stalls (or it is super slow) to move to the next experience.
**To Reproduce**
```
import torch
import torch.optim as optim
import torchvision.…
-
We should check & update the API doc for every module:
- [x] Benchmarks - @lrzpellegrini
- [x] Training - @AntonioCarta
- [x] Evaluation - @AndreaCossu
- [x] Logging - @AndreaCossu
- [x] Mo…
-
-
Hi,
we are developing and maintaining a library gathering continual learning scenarios (https://github.com/Continvvm/continuum).
Would you be interested in adding your dataset into our library?
…
-
**Description**
When looking at the code for agem.py (in the before_training_iteration function), it appears that the reference gradient is computed w.r.t the head of the current task as opposed to …
-
Hello everyone, following #293 and #313, I propose the following changes to both steps and the Transformation Dataset:
1) Rename `StepInfo` to `Experience`.
2) In `Experience`, support multiple ta…