Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / KevinMusgrave/pytorch-metric-learning issues and pull requests

#717 - KeyError in load_model()

Issue - State: open - Opened by ManuelZ 13 days ago - 1 comment

#715 - Evaluating big datasets on GPU

Issue - State: closed - Opened by ir2718 21 days ago - 3 comments

#714 - Corrected the paper reference in the CosFace loss

Pull Request - State: closed - Opened by elisim 23 days ago - 1 comment

#712 - Wrapping NTXentLoss in DistributedLossWrapper makes loss extremely high

Issue - State: closed - Opened by irowberryFS about 1 month ago - 6 comments

#711 - Confused about SelfSupervisedLoss and labeling with dataset of pairs

Issue - State: closed - Opened by irowberryFS about 1 month ago - 6 comments

#710 - Wrapping the loss with DistributedDataParallel

Issue - State: open - Opened by elisim about 2 months ago - 1 comment

#709 - Accuracy for Face Identification, Need some examples for AccuracyCalculator

Issue - State: open - Opened by f-izzat about 2 months ago - 1 comment

#708 - Quadruplet Miners

Issue - State: open - Opened by Mahendra114027 about 2 months ago - 1 comment
Labels: enhancement

#706 - UnboundLocalError: local variable 'all_q' referenced before assignment

Issue - State: closed - Opened by zxlml 2 months ago - 1 comment

#705 - Another ntxent loss question

Issue - State: closed - Opened by Stas384 2 months ago - 4 comments

#704 - v2.6.1

Pull Request - State: closed - Opened by KevinMusgrave 2 months ago

#703 - v2.6.0

Pull Request - State: closed - Opened by KevinMusgrave 2 months ago

#702 - DistributedLossWrapper enhancements

Pull Request - State: closed - Opened by elisim 2 months ago - 4 comments

#701 - arguments names are different in forward in when using the DDP wrapper

Issue - State: closed - Opened by elisim 2 months ago - 1 comment

#700 - Distributed training not using all available GPUs on large dataset

Issue - State: closed - Opened by ritamyhuang 3 months ago - 2 comments

#699 - InfoNCE errors

Issue - State: closed - Opened by davidireland3 3 months ago - 4 comments

#697 - Allow additional parameters in `compute_mat`

Issue - State: open - Opened by celsofranssa 4 months ago - 10 comments
Labels: enhancement

#696 - NTXentLoss, normalize issue.

Issue - State: closed - Opened by jzhanghzau 5 months ago - 3 comments

#694 - DDP and Faiss TemporaryMemoryBuffer error

Issue - State: open - Opened by vemchance 5 months ago - 4 comments

#692 - v2.5.0

Pull Request - State: closed - Opened by KevinMusgrave 6 months ago

#690 - Model overfitting, smooth triplet margin loss

Issue - State: open - Opened by taaresh7 6 months ago - 2 comments

#687 - CASIA Face Recognition

Issue - State: open - Opened by gauravkuppa 7 months ago - 4 comments

#686 - InfoNCE of pre-defined anchor, positive and negative pairs

Issue - State: closed - Opened by alaaj27 7 months ago - 1 comment

#685 - The split of the Stanford Cars dataset.

Issue - State: closed - Opened by ppanzx 8 months ago - 1 comment

#684 - Bug in MPerClassSampler: It does not select all classes and samples in each epoch of training

Issue - State: open - Opened by Jalilnkh 8 months ago - 1 comment
Labels: enhancement

#683 - Neural representation similarities

Issue - State: open - Opened by domenicoMuscill0 8 months ago - 7 comments

#682 - Normalised embeddings when using a combination of miners and losses.

Issue - State: closed - Opened by riririririi 9 months ago - 2 comments

#681 - Contrastive loss using only indices_tuple without labels.

Issue - State: closed - Opened by fdila 9 months ago - 2 comments
Labels: documentation

#680 - Consider importing submodules in top level __init__ and using lazy importing

Issue - State: open - Opened by KevinMusgrave 9 months ago
Labels: enhancement

#679 - master into dev

Pull Request - State: closed - Opened by KevinMusgrave 10 months ago

#678 - v2.4.1: use `license_files` in setup.py

Pull Request - State: closed - Opened by KevinMusgrave 10 months ago

#677 - v2.4.0

Pull Request - State: closed - Opened by KevinMusgrave 10 months ago

#676 - add introduction of PNP Loss

Pull Request - State: closed - Opened by interestingzhuo 10 months ago - 3 comments

#675 - NDCGLoss

Issue - State: open - Opened by celsofranssa 10 months ago
Labels: new algorithm request

#674 - While updating conda(installing current version), I found some erros, how to solve it?

Issue - State: closed - Opened by SC-PIONEER 11 months ago - 2 comments
Labels: pip/conda

#673 - PNPLoss

Issue - State: closed - Opened by celsofranssa 11 months ago - 15 comments
Labels: documentation

#672 - Use the trained model as a classifier?

Issue - State: closed - Opened by kexul 11 months ago - 2 comments

#671 - Add MultipleNegativesRankingLoss

Pull Request - State: closed - Opened by mcschmitz 12 months ago - 3 comments

#670 - Default normalization in distances is counterintuitive (or wrong)

Issue - State: open - Opened by mcschmitz 12 months ago - 1 comment
Labels: bug, documentation

#669 - Hello , Is this package able to train a multi-label dataset with one-hot encoding?

Issue - State: open - Opened by Mahiro2211 12 months ago - 2 comments
Labels: enhancement

#668 - fix test_histogram_loss

Pull Request - State: closed - Opened by GaetanLepage 12 months ago - 1 comment

#667 - Multi-SupConLoss

Pull Request - State: open - Opened by PhyseChan 12 months ago

#666 - What should be embedding size in ArcFace Loss

Issue - State: closed - Opened by ashray21 12 months ago - 4 comments
Labels: question

#664 - Add MultipleNegativesRanking Loss

Issue - State: closed - Opened by mcschmitz about 1 year ago - 2 comments
Labels: new algorithm request

#663 - Suggestion on loss function and other combinations

Issue - State: closed - Opened by jainrahulsethi about 1 year ago - 5 comments
Labels: question

#661 - Few-shot learning

Issue - State: closed - Opened by westbalon about 1 year ago - 1 comment
Labels: question

#660 - Fix PNP loss to make it work with negatives without related positives

Pull Request - State: closed - Opened by Puzer about 1 year ago - 3 comments

#659 - Dynamic soft margin loss & Ranked List Loss

Pull Request - State: closed - Opened by domenicoMuscill0 about 1 year ago - 5 comments

#658 - Multi-label version of SupConLoss

Issue - State: open - Opened by penguinwang96825 about 1 year ago - 2 comments
Labels: new algorithm request

#657 - how to train using classfier without trainer

Issue - State: closed - Opened by sofpya about 1 year ago - 1 comment
Labels: question

#653 - v2.3.0

Pull Request - State: closed - Opened by KevinMusgrave about 1 year ago

#652 - error while training

Issue - State: closed - Opened by pheersaquoff about 1 year ago - 5 comments
Labels: question

#651 - Histogram loss

Pull Request - State: closed - Opened by domenicoMuscill0 about 1 year ago - 5 comments

#650 - Adding details to NTXentLoss documentation

Pull Request - State: closed - Opened by stompsjo about 1 year ago - 1 comment

#649 - Reduction type for NTXentLoss should be "element"

Issue - State: closed - Opened by KevinMusgrave about 1 year ago - 1 comment
Labels: enhancement

#648 - Combining two loss functions

Issue - State: closed - Opened by HarryP23 about 1 year ago - 1 comment
Labels: question

#647 - Can MatchFinder implement the query library?

Issue - State: closed - Opened by ZH-UCAS about 1 year ago - 1 comment
Labels: question

#646 - Simplify reducers & mixin

Pull Request - State: open - Opened by domenicoMuscill0 about 1 year ago

#645 - Sample triplets obtained with TripletMarginMiner to reduce memory usage

Issue - State: closed - Opened by nefagi-01 about 1 year ago - 1 comment
Labels: question

#644 - Fix typo

Pull Request - State: closed - Opened by bot66 over 1 year ago - 1 comment

#643 - Fixed issues #491, #430 and #602

Pull Request - State: open - Opened by domenicoMuscill0 over 1 year ago - 3 comments

#642 - distributed training bug fix, to maintain same order for mem queue fo…

Pull Request - State: open - Opened by zhaoyuac09 over 1 year ago - 16 comments

#641 - Add information for contributors

Issue - State: open - Opened by domenicoMuscill0 over 1 year ago
Labels: documentation

#640 - Make `to_device` support list inputs

Issue - State: open - Opened by KevinMusgrave over 1 year ago
Labels: enhancement

#639 - Bug for distributed wrapper regarding to cross batch memory loss

Issue - State: open - Opened by zhaoyuac09 over 1 year ago - 5 comments
Labels: bug

#638 - master into dev

Pull Request - State: closed - Opened by KevinMusgrave over 1 year ago

#636 - Question about accuracy calculation in test script

Issue - State: closed - Opened by learnfromgroundup over 1 year ago - 1 comment
Labels: question

#635 - Manifold Loss and P2SGrad Loss

Pull Request - State: closed - Opened by domenicoMuscill0 over 1 year ago - 11 comments

#634 - v2.2.0

Pull Request - State: closed - Opened by KevinMusgrave over 1 year ago

#633 - Create example to show how SelfSupervisedLoss works

Issue - State: open - Opened by KevinMusgrave over 1 year ago
Labels: documentation

#631 - v2.1.2

Pull Request - State: closed - Opened by KevinMusgrave over 1 year ago

#630 - SelfSupervisedLoss should compute with both `(emb, ref_emb)` and `(ref_emb, emb)`

Issue - State: closed - Opened by KevinMusgrave over 1 year ago - 1 comment
Labels: enhancement

#629 - Using Pytorch Metric Learning for dual encoder structure for question answering (Q&A)

Issue - State: closed - Opened by puzzlecollector over 1 year ago - 2 comments
Labels: question

#628 - Stats are not recorded TripletMarginMiner

Issue - State: closed - Opened by nefagi-01 over 1 year ago - 1 comment
Labels: bug

#627 - Running error about the tutorial of MoCoCIFAR10

Issue - State: closed - Opened by yuxiaokang-source over 1 year ago - 4 comments
Labels: question

#626 - What is the meaning of label in TwoStreamMetricLoss

Issue - State: closed - Opened by brianw0924 over 1 year ago - 2 comments
Labels: question

#625 - NTXentLoss with custom miner

Issue - State: closed - Opened by brianw0924 over 1 year ago - 2 comments
Labels: question

#624 - What c_f.process_label actually does?

Issue - State: closed - Opened by brianw0924 over 1 year ago - 2 comments
Labels: question

#623 - Different loss_fn for trunk and embedder

Issue - State: closed - Opened by brianw0924 over 1 year ago - 2 comments
Labels: question

#622 - Clarification on Negative Pair Selection for NTXentLoss Function

Issue - State: closed - Opened by ZhouMengjie over 1 year ago - 1 comment
Labels: question

#621 - v2.1.1

Pull Request - State: closed - Opened by KevinMusgrave over 1 year ago

#620 - Possible bug in assignment of initial_avg_query_norm

Issue - State: closed - Opened by rheum over 1 year ago - 2 comments
Labels: bug

#619 - Why do I get diffrent results of outlier?

Issue - State: closed - Opened by kurose635 over 1 year ago - 4 comments
Labels: question

#618 - Faiss throws up TypedStorage is Deprecated UserWarning

Issue - State: closed - Opened by chichieinstein over 1 year ago - 4 comments

#616 - Index Error method get_target_mask using CosFaceLoss

Issue - State: closed - Opened by jailsonpj over 1 year ago - 4 comments
Labels: question

#615 - Update samplers.md

Pull Request - State: closed - Opened by rheum over 1 year ago

#614 - Remove `indices_tuple` argument from CrossBatchMemory

Issue - State: open - Opened by KevinMusgrave over 1 year ago
Labels: enhancement

#612 - Convert MPerClassSampler to a `batch_sampler`

Issue - State: open - Opened by KevinMusgrave over 1 year ago
Labels: enhancement

#611 - MPerClassSampler: 'numpy.int32' object is not iterable

Issue - State: closed - Opened by rheum over 1 year ago - 4 comments
Labels: question

#609 - Question about the usage of NTXentLoss along with CrossBatchMemory

Issue - State: closed - Opened by HaominJiang over 1 year ago - 15 comments
Labels: question

#608 - Explain more clearly how NTXentLoss works

Issue - State: closed - Opened by KevinMusgrave over 1 year ago - 1 comment
Labels: documentation

#605 - v2.1.0

Pull Request - State: closed - Opened by KevinMusgrave over 1 year ago

#604 - Stratified Sampler with NTXent + Cross-Batch -- Cuda Error

Issue - State: closed - Opened by sapan over 1 year ago - 2 comments
Labels: question