Frank

I think, the issue is a little bit more complicated. As the docstring says, the `metric` that is passed to the `get_performance_dictionary` determines "how to decide the best setting". Currently,...

We will do the following steps for version 1.2.0: - [ ] Add full support for PyTorch Added to the first post.

Hey, it is indeed only partially solved on the development branch or the pre-release `1.2.0-beta.` Most of the test problems are translated to PyTorch and are fully functioning (including the...

Hi @tvogels, great to here it! There is actually a PR that introduces the Tolstoi RNN task to PyTorch: #40. I am currently working on a refactoring of DeepOBS for...

That is great, thank you so much. I hope in a few days I have some time to merge it. I want to add a "contributors" section to the readme....

Thanks, I will. Don't worry about the checks. They are currently not perfectly set up and alert on some false positives. I will fix this. Thanks again for your contribution.

Sorry, I didn't see this issue until today, so hence my late response. But Ludwig already gave the right answer. The "train eval" set is by design a subset of...

We will do the following steps for version 1.2.0: - [x] Include a validation set for PyTorch (needs to be merged from Aaron's branch) - [x] Include a validation set...

Just wanted to give an update: We now have a validation set for PyTorch and TensorFlow in the [development branch](https://github.com/fsschneider/DeepOBS/tree/v1.2.0-beta0). I also included a graphic with the setup for those...

I am closing this issue as it is stale. Please feel free to open it again if you have further questions.