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.

The default RubrixLogHTTPMiddleware record mapper for token classification expect a structured including a text field for inputs. This could make prediction model inputs a bit cumbersome. Default mapper could accepts also flat strings as inputs:

def token_classification_mapper(inputs, outputs):
    i

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.

For the auto-generated pages on the readthedocs, the edit on GitHub button is still available but links to a 404 page.

See: https://asreview.readthedocs.io/en/latest/API/generated/asreview.models.base.BaseModel.html

Traceback (most recent call last):
File "tools/train.py", line 257, in
main()
File "tools/train.py", line 170, in main
distributed=distributed, validate=(not args.no_validate), timestamp=timestamp, meta=meta)
File "/media/gc/1T/MI-AOD-master/mmdet/apis/train.py", line 120, in train_detector
runner.run(data_loaders_L, cfg.workflow, cfg.total_epochs)
File "/home/g