Dante Basile

Results 2 issues of Dante Basile

### Background A loss function suitable for unsupervised learning would contribute to extending ProgLearn's training domain to unsupervised settings in which labeled data are not available. The unsupervised contrastive loss...

ndd

**Reference issue** #520 **Type of change** This contains the loss function and a basic ResNet50 demo demonstrating training and decreasing loss on CIFAR-10. **What does this implement/fix?** This demonstrates that...