Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision
Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision
复制标题
Torch.manual_seed(3407) 就是您所需要的：关于计算机视觉深度学习架构中随机种子的影响
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
David Picard
中科院分区：
文献类型：
--
作者：
David Picard
在本文中，我研究了随机种子选择在使用流行的计算机视觉深度学习架构时对准确性的影响。我在CIFAR 10上扫描了大量的种子（高达10^4美元），我也在Imagenet上扫描了较少的种子，使用预训练的模型来研究大规模数据集。结论是，即使差异不是很大，也很容易找到一个表现比平均水平好得多或差得多的异常值。
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.