* chore: update pre-commit versions
* ci: remove old configurations
* ci: copy workflow from prototorch
* ci: run precommit for all files
* ci: add examples CPU test
* ci(test): failing example test
* ci: fix workflow definition
* ci(test): repeat failing example test
* ci: fix workflow definition
* ci(test): repeat failing example test II
* ci: fix test command
* ci: cleanup example test
* ci: remove travis badge
Siamese architectures no longer accept a `backbone_module`. They have to be
initialized with an pre-initialized backbone object instead. This is so that the
visualization callbacks could use the very same object for visualization
purposes. Also, there's no longer a dependent copy of the backbone. It is
managed simply with `requires_grad` instead.
Pass the component initializer as an hparam slows down the script very much. The
API has now been changed to pass it as a kwarg to the models instead.
The example scripts have also been updated to reflect the new changes.
Also, ImageGMLVQ and an example script `gmlvq_mnist.py` that uses it have also
been added.
