Pytorch-metric-learning

Bug fixes and minor improvements

- Fixed 472, in which `enqueue_idx` for CrossBatchMemory could not be passed into DistributedLossWrapper
- Converted CrossBatchMemory's `embedding_memory` and `label_memory` to buffers, so they can be saved and loaded as state dicts and transferred to devices use `.to(device)`.

Minor improvement

Resolved https://github.com/KevinMusgrave/pytorch-metric-learning/issues/565

Features and bug fixes

- Added SumReducer
- Fixed bug where labels were always required for DistributedLossWrapper
- Removed torchvision as a dependency

Bug fixes

Fixes an edge case in ArcFaceLoss. Thanks ElisonSherton!

Relevant links:

- https://github.com/KevinMusgrave/pytorch-metric-learning/issues/537
- https://github.com/KevinMusgrave/pytorch-metric-learning/pull/539
- https://github.com/deepinsight/insightface/issues/2126
- https://github.com/ronghuaiyang/arcface-pytorch/issues/48

Bug Fixes

- Fixed bug where `DistributedMinerWrapper` would crash when `world_size == 1` (542)