**Losses**
* Added ProxyAnchorLoss
**Trainers**
* BaseTrainer
* Made iterations_per_epoch optional. See the [new documentation](https://kevinmusgrave.github.io/pytorch-metric-learning/trainers/#basetrainer)
* Changed keys for lr_schedulers to allow for end of iteration, end of epoch, and plateau schedulers to all be used at the same time.
* Fixed a key verification bug in BaseTrainer.
**Utils**
* HookContainer
* Added skip_eval_if_already_done flag to run_tester_separately.
* Made ignore_epoch a tuple.
* Added save_custom_figures flag.
* Made records get saved before models.
* common_functions
* Removed pass_data_to_model and autograd.Variable usage.
**Other stuff**
* Fixed bug where __version__ was not accessible.
* Added test for pair and triplet index computation