Delira

Added

* [TensorFlow](https://tensorflow.org) support including
- `AbstractTfNetwork`
- `TfNetworkTrainer`
- `TfExperiment`
- `ClassificationNetworkBaseTf`

* Basic Test-API in `Experiment` ([commit](https://github.com/justusschock/delira/commit/45d30addc65fd0df64fb23676efa163a70609e1a))
* More Unittests
* Methods to get a subset of each Dataset
* Stratified Kfold

Bugfixes
* dropping last batch in `PyTorchNetworkTrainer.predict` ([commit](https://github.com/justusschock/delira/commit/99a7801c12407705ef5c4fcc5504df6601f6ecee))
* Check for installed backends

Based on [PyTorch](https://pytorch.org), [batchgenerators](https://github.com/MIC-DKFZ/batchgenerators) and [trixi](https://github.com/MIC-DKFZ/trixi) it provides a framework for
* Dataset loading
* Dataset sampling
* Augmentation (multi-threaded) including 3D images with any number of channels
* A generic trainer class that implements the training process
* Already implemented [models](delira/models) used in medical image processing and exemplaric implementations of most used models in general (like Resnet)
* Web-based monitoring using [Visdom](https://github.com/facebookresearch/visdom)
* Model save and load functions