Hamed

@shekkizh thanks for reporting the issue. Are you using the Beta version (0.1.0) of Avalanche? If yes, I guess the "extremely slow" running time is due to the way replay...

Hi @matkowski-voy ! The batch size for the replay dataloader is equal to `2 x batch_size` by default because it concatenate two batches of the same size, one from the...

As discussed in the previous meeting, creating new templates with the current structure will result in lots of code duplicates. For example if we want to have a separate template...

Follow-up comment on @AntonioCarta's: Here is a paper showing that SI and LwF almost fail in class-incremental scenarios for Split-MNIST: https://arxiv.org/pdf/1904.07734.pdf  By changing your...

@AntonioCarta There is also another point regarding plugins: I thought about implementing an existing meta-learning-based strategy as a plugin for `SupervisedMetaLearningTemplate` and realized that we also need to include inner/outer...

- The meta-update class is updated. - @AntonioCarta I applied some of your comments, for the other comments I need to discuss them with you in the next meeting. -...

@AntonioCarta the updates are made according to our last discussion.

Update: - Old template files are removed, and all imports are updated - `_train_exp` is removed from `observation_type`now it's a part of the `BasedSGDTemplate` again - `observation_type` now only checks...

Hi @alaa-shubbak ! Did you install avalanche with the detection packages, i.e. `pip install avalanche-lib[detection]`? Have a look at here the link below for more details: https://avalanche.continualai.org/getting-started/how-to-install

@alaa-shubbak It seems like `lvis_dataset` is not included in `avalanche.benchmark.dataset` imports. Can you change the following import line in the `detection_levis` example: `from avalanche.benchmarks.datasets import LvisDataset` -> `from avalanche.benchmarks.datasets.lvis_dataset import...