Slightly different strength parameter in CIFAR-10 setting

[nzw0301]

Hi, thank you for sharing SimCLRv1 code by using pytorch. This repo is really helpful.

I realised that the strength parameter s of ColorJitter is slightly different from the paper's setting.
Appendix B.9. CIFAR-10 of SimCLRv1 paper says

color distortion (strength=0.5),

So, we need to set s=0.5 for CIFAR-10 experiments if we obtain the experimental results more accurately.

Best regards,

[gauenk]

you are correct. the value should be 0.5 according to the paper