Features
- Added a batch_size parameter to [CustomKNN](https://kevinmusgrave.github.io/pytorch-metric-learning/inference_models/#customknn). This computes k-nn per batch of query embeddings (using [BatchedDistance](https://kevinmusgrave.github.io/pytorch-metric-learning/distances/#batcheddistance)), which requires less memory than computing the entire distance matrix at once.
Bug Fixes
- 451 (thanks cwkeam)
- 453