Why is there no validation loss?

sthalles / SimCLR

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

https://sthalles.github.io/simple-self-supervised-learning/

MIT License

2.19k stars 457 forks source link

Why is there no validation loss? #31

Open ackbar03 opened 3 years ago

ackbar03 commented 3 years ago

Hi, thanks very much for providing the code and framework!

Can I check why the code does not monitor loss evolution for a separate validation set? I see from the closed issues that there used to be one, but it seems to have been removed in latest. I'm sure validation loss should still be monitored to ensure model learns proper features right?

Thanks! Michael

here101 commented 2 years ago

I think the evaluation code may be the ipynb in the feature_eval folder,and the ipynb need to be run in the google colab.