相同seed，不同方法差2%呢？
【 在 GoSox 的大作中提到: 】
:
https://arxiv.org/abs/2109.08203: Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision
: On a scanning of 10^4 seeds, we obtained a difference between the maximum and minimum accuracy close to 2% which is above the threshold commonly used by the computer vision community of what is considered significant.
--
FROM 223.80.54.*