Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision

In this paper I investigate the effect of random seed selection on the\naccuracy when using popular deep learning architectures for computer vision. I\nscan a large amount of seeds (up to $10^4$) on CIFAR 10 and I also scan fewer\nseeds on Imagenet using pre-trained models to investigate large scale datasets.\nThe conclusions are that even if the variance is not very large, it is\nsurprisingly easy to find an outlier that performs much better or much worse\nthan the average.\n