New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
关于CPNet训练问题 #4
Comments
不正常。 我在1张V100上用默认参数(但batch size改成8)训练,开始几个iteration之后Color L1 loss就会降到0.02-0.05的水平。 我也检查了多卡跑起来会不会出错,此时用了4张V100(batch size此时为32),开始几个iteration之后Color L1 loss也会在0.03左右。 建议检查下data读取是不是有问题? |
|
是啊,clone下来跑的,是linux,就改了个batch size |
Hi, menghuaa 好久之前训的,具体训练策略写在paper里了,建议先看论文的描述 查了下论文,是 batchsize=4 per GPU and 8 NVIDIA Titan Xp GPUs。具体损失降到多少记不清楚了,我提供了预训练模型,可以加载第一阶段的CPNet接着训就知道loss大概是多少了 关于稳定性的问题,或许是因为之前网络没有采用任何normalization的原因。可以改变下网络initialization策略和调低学习率?这样训练可能更容易一点? |
您好,我下载了您给的ILSVRC2012数据集,在训练的时候loss感觉没啥显著变化,请问正常吗?loss值大概一直都在下图所示的值附近徘徊,我用了4张A6000训练,没有改变任何参数
The text was updated successfully, but these errors were encountered: