[2109.08203] Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision
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.
View PDF HTML (experimental) 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. Comments: fixed typos Subjects: Computer Vision and Pattern Recognition (cs.CV)…
saved by
related reading
- (Some of) The Models, They Just Don't Want to Learn | Tildeblog.tilderesearch.com
- How our data shaped neural architecture discovery, and how automation can reshape the future | Core Automationcoreauto.com
- Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
- The Decade of Deep Learning | Leo Gaobmk.sh
- A Recipe for Training Neural Networkskarpathy.github.io
- The Little Book of Deep Learningfleuret.org
- Understanding deep learning requires rethinking generalizationarxiv.org
- A Recipe for Training Neural Networkskarpathy.github.io
- David Duvenaudcs.toronto.edu
- GitHub - google-research/tuning_playbook: A playbook for systematically maximizing the performance of deep learning models.github.com
- [2203.09795] Three things everyone should know about Vision Transformersarxiv.org
- Domain randomization for neural network classification - PMCncbi.nlm.nih.gov