Continuation of issue #2474 as discussed here

Add default parameters for all projection heads

It's helpful to know what the default parameters were in the papers to get started. We should add the default projection head parameters which were used for pre-training on Imagenet to all projection and prediction heads in lightly/models/modules/heads.py.

When computing the isosurface, when 4 simplex edges crosses the isosurface, we add 2 triangles to the isosurface triangulation.

Right now we add these arbitrarily (in these 3 lines) but we should add them so that the curvature is minimized.

The current state o

We need a per-technique way of resetting a Module.

For bayesian.dropout we need to reset the Dropout Layer
For bayesian.dropconnect we need to make the layers deterministic again.

This PR adds the option to re-import RIS files into reference software to the documentation.

To do:

• add more information on how the labels are stored in which field of the RIS file (@ottomattas )
• add a screenshot of how this looks in reference manager software (@ottomattas )