pytorch-metric-learning
pytorch-metric-learning copied to clipboard
KevinMusgrave
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.
"ProxyNCA++ adds enhancements to ProxyNCA and achieves a 22.9 percentage point average improvement of Recall@1 across four different zero-shot retrieval datasets compared to the original ProxyNCA algorithm. Furthermore, we achieve...
[As mentioned here](https://github.com/KevinMusgrave/pytorch-metric-learning/issues/98#issuecomment-629239677) this is a possible improvement to make it easier for people to log the attributes in the "record_these" lists.
It would be nice to have a trainer for [MoCo](https://arxiv.org/abs/1911.05722). It would be similar to [UnsupervisedEmbeddingsUsingAugmentations](https://github.com/KevinMusgrave/pytorch-metric-learning/blob/master/src/pytorch_metric_learning/trainers/unsupervised_embeddings_using_augmentations.py) but would need to use [CrossBatchMemory](https://github.com/KevinMusgrave/pytorch-metric-learning/blob/master/src/pytorch_metric_learning/losses/cross_batch_memory.py) for the queue. Also, since the queue has...
Is there any reason not to include it here? :) Learning Deep Embeddings with Histogram Loss Evgeniya Ustinova, Victor Lempitsky https://arxiv.org/pdf/1611.00822.pdf
https://arxiv.org/abs/1905.02479
https://github.com/computationalmodelling/nbval
Will you consider to add to this library some similarities among neural network representations? Like CCA or CKA for example.
First of all, I really appreciated this repo. Thank you very much for the repo! However, there is a function will not work logically, in m_per_class_sampler.py for the classes and...
First of all, I really appreciated this repo. Thank you very much for the contribution! However, there are 2 functions will not work logically, in distributed.py for the loss and...
Metadata
Owner
Metadata
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.