PyTorch Metric Learning
This work addresses the implementation barrier for researchers and practitioners in deep metric learning, though it is incremental as it builds on existing algorithms rather than introducing new ones.
The authors tackled the problem of tedious and time-consuming implementation of deep metric learning algorithms by developing PyTorch Metric Learning, an open-source library that provides modular and flexible design for easy integration and complete train/test workflows, resulting in faster results for users.
Deep metric learning algorithms have a wide variety of applications, but implementing these algorithms can be tedious and time consuming. PyTorch Metric Learning is an open source library that aims to remove this barrier for both researchers and practitioners. The modular and flexible design allows users to easily try out different combinations of algorithms in their existing code. It also comes with complete train/test workflows, for users who want results fast. Code and documentation is available at https://www.github.com/KevinMusgrave/pytorch-metric-learning.