HackerPapers

arXiv:2109.08203cs.CV

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

David Picard

Abstract

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

arXiv comments
fixed typos
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition

On Hacker News

Linked by 3 identifiable commenters in 3 comments across 3 threads, from May 2023 to Jan 2025. Found in 3 HN submissions from May 2023 to Oct 2024. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments3 threads

    • Hey! :) Coincidentally the seeds I always use are 3407, 3408 and 3409 :) 3407 because of https://arxiv.org/abs/2109.08203 I also tried not setting the seeds, but the results are still the same - quantizing all layers seems to make the model forget and repeat everything - I put…

      danielhanchenView on HNParent context

    • You may enjoy this article: https://arxiv.org/abs/2109.08203 The author treats the seed as a hyperparameter and searches for the one that performs best for training a CV model.

      mcycView on HNParent context

    • This is not always true. ML has reproducibility issues despite the status quo being open models. Even if we don't include proprietary datasets there are still issues. Compute is one issue, but we can even ignore that[0]. The Lottery Ticket[1,2] plays a big role, in that you can…

      godelskiView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.