v1.5.1

Bug fixes

Bumped the record-keeper version to fix issue #497

v1.5.0

Features

For some loss functions, labels are now optional if indices_tuple is provided:

loss = loss_func(embeddings, indices_tuple=pairs)

The losses for which you can do this are:

• CircleLoss
• ContrastiveLoss
• IntraPairVarianceLoss
• GeneralizedLiftedStructureLoss
• LiftedStructureLoss
• MarginLoss
• MultiSimilarityLoss
• NTXentLoss
• SignalToNoiseRatioContrastiveLoss
• SupConLoss
• TripletMarginLoss
• TupletMarginLoss

This issue has come up several times:

#412
#490
#482
#473
#179
#263

v1.4.0

New features

• Added InstanceLoss. See #410 by @layumi

v1.3.2

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

v1.3.1

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.

v1.3.0

Features

• Added a batch_size parameter to CustomKNN. This computes k-nn per batch of query embeddings (using BatchedDistance), which requires less memory than computing the entire distance matrix at once.

Bug Fixes

• #451 (thanks @cwkeam)
• #453

v1.2.1

Bug Fixes

• #447

v1.2.0

New Loss Function: SubCenterArcFace

• Documentation
• Example notebook
• Paper
• Issue
• Pull Request

Thanks @chingisooinar!

v1.1.2

Bug fixes

• #427
• #428

v1.1.1

Bug fixes

• #420
• #422