roman807

Currently we get the split from the dataloader_idx. This requires a `dataloader_idx_map` and a list of predict-datasets in the corresponding order. To make this more robust and allow one predict-dataset...

Main issue for all tasks concerning slide-level inference support. - [x] https://github.com/kaiko-ai/eva/issues/363 - [x] https://github.com/kaiko-ai/eva/issues/364 - [x] https://github.com/kaiko-ai/eva/issues/374 - [ ] https://github.com/kaiko-ai/eva/issues/375 - [x] https://github.com/kaiko-ai/eva/issues/376

Add logistic regression with grid search

1

As an alternative to MLP, we want to allow using a logistic regression head (+ grid search to find the best hyperparameters C1 & C2). TBD, but likely it would...

[OpenSSF](https://www.bestpractices.dev/en) provides a blueprint for following best practices with open source code. Many popular open-source projects (e.g. TensorFlow) obtained their badge - during development we want to keep following their...

In experiments with the segmentation protocol used for MoNuSAC and CoNSeP, BCSS didn't add much value as an additinol segmentation task, because: - it didn't differentiate well between models (~1%...

closes https://github.com/kaiko-ai/eva/issues/681

Add HEROHE as downstream task: https://ecdp2020.grand-challenge.org/Dataset/ to identify Her2 (slide level task, binary classification, 500 training / 362 test samples) Background info: HER2 is a protein receptor which is amplified/overexpressed...