Pytorch-metric-learning

Latest version: v2.7.0

Safety actively analyzes 682471 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 5 of 9

1.3.2

Bug fixes

- Fixed a bug in BatchEasyHardMiner where `get_max_per_row` was not always returning correct values, resulting in invalid pairs and triplets. 476

1.3.1

Bug fixes

- Fixed ThresholdReducer being incompatible with older versions of PyTorch (465)
- Fixed VICRegLoss being incompatible with older versions of PyTorch, and missing a division by 2 (467 and 470 by cwkeam)

Other

- Made CustomKNN more memory efficient by removing `torch.cat` call.

1.3.0

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

1.2.1

Bug Fixes

- 447

1.2.0

New Loss Function: SubCenterArcFace

- [Documentation](https://kevinmusgrave.github.io/pytorch-metric-learning/losses/#subcenterarcfaceloss)
- [Example notebook](https://github.com/KevinMusgrave/pytorch-metric-learning/blob/master/examples/notebooks/SubCenterArcFaceMNIST.ipynb)
- [Paper](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123560715.pdf)
- [Issue](https://github.com/KevinMusgrave/pytorch-metric-learning/issues/208)
- [Pull Request](https://github.com/KevinMusgrave/pytorch-metric-learning/pull/424)

Thanks chingisooinar!

1.1.2

Bug fixes

- 427
- 428

Page 5 of 9

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.