Release v0.2.1

Release notes:

• Fix error message in DataLoaderIter.inputs_labels_from_batch()
• Fix flat loss when using a validation dataset (#59, #60)
• Fix issue #57 by determining the batch size from the size of the labels instead of the size of the inputs (#58)
• Add optional argument to LRFinder.plot() for plotting a suggested learning rate (#44). The optional argument is suggest_lr

Release v0.2.0

Release notes:

• Command to install apex changed from pip install torch-lr-finder -v --global-option="amp" to pip install torch-lr-finder -v --global-option="apex"
• Handle apex install for pytorch < 1.0.0
• Remove message checking if the apex.amp module is available (#46)
• Fix learning rate history and learning rate computation in schedulers (#43, #42)
• Refactor of Dataloader iterator wrapper (#37). An example of how this can be used can be found in examples/lrfinder_cifar10_dataloader_iter
• Transfer data to cuda with non_blocking=True (#31)
• Enable batch data contained in a dictionary to be moved to the correct device (#29)
• Enable generic objects to be moved to the correct device if they have a .to() method (#29)
• Dropped Python 2.x support: the last version with Python 2 support is v0.1.5 which can also be found in the torch_lr_finder-v0.1 branch

Extended iterable unpacking fix for Python 2.7

Fixed extended iterable unpacking for Python 2.7 as proposed by @NaleRaphael in #27.