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

Source: [Torch.manual\_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision](<https://www.sota2.com/research/paper/68fa6f481e209131cea44bc7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:17:36.551Z

Authors: David Picard

Published: 2021-09-16T20:10:12.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2109.08203>)

[PDF](<https://arxiv.org/pdf/2109.08203.pdf>)