SimCLR implementation- NT-Xnet Loss
This is video no. 6 in a series walking through simCLR research paper, going over the NT-Xnet loss implementation.
William Falcon, PyTorch Lightning founder, and Ananya Harsh Ja, Lightning research engineer, deep dive into simCLR (“A Simple Framework for Contrastive Learning of Visual Representations”), self-supervised representation learning on images. Start here for simCLR overview: https://www.youtube.com/watch?v=pDJx8i3jenA&list=PLaMu-SDt_RB4k8VXiB3hOdsn0Y3GoXo1k
In the next videos, we will go over other key ideas of the paper, and how they are implemented with PyTorch Lightning.
Next: Global Batch Norm – https://youtu.be/4wddWrTlLsw
PyTorch Lightning implementation: https://github.com/PyTorchLightning/pytorch-lightning-bolts/tree/master/pl_bolts/models/self_supervised/simclr
Thanks for watching! Please Subscribe!