Antonio Carta

periodic eval is broken in some subtle cases. Instead of calling `eval` on the entire stream, it calls it multiple times for each experience, breaking stream-level metrics. Reproduce: ``` from...

ADD Meta Learning Template

2

@HamedHemati

See #1082 for a benchmark.

@JuliousHurtado

ADD methods to apidoc

2

We would like to have methods documented in the apidoc. The main roadblock right now is that the doc building is killed due to excessive time/memory consumption. See #1059

Avalanche Roadmap to Beta-2 (v0.2.0)🚀

5

I'm opening this issue to keep track of the multiple issues that we have to fix before the next version. Feel free to edit it. **Benchmarks** - [x] support for...

Examples in the documentation

2

We should add some examples in the classes documentation, at least for the high level classes and all the features more frequently used by the end user. I think pytorch...

There is something weird going on. Every time the ContinualAI-bot makes a commit to this repo, it also changes files that have already been updated ([example](https://github.com/ContinualAI/avalanche/commit/3b4d8b3bd8dc7abcd8676632ded3343ba6c89d21)). maybe the github actions...

The bug can be reproduced with the following script: ``` from torch.utils.data import random_split from avalanche.benchmarks import SplitMNIST from avalanche.benchmarks.utils.data_loader import TaskBalancedDataLoader benchmark = SplitMNIST(5) data = benchmark.train_stream[0].dataset rem_len =...