-
Notifications
You must be signed in to change notification settings - Fork 7
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
训练时间+GPU是否利用问题 #14
Comments
@WeiCL7777 你好,时间太长了,我不记得了,按理说256*256的不可能bs=4就爆显存,可能你需要仔细检查一下两边的代码了,看看是你resnet加载成101了还是数据增强部分有问题? |
@WeiCL7777 另外,在这几个仓库的isue中,也有人做过变化检测,但是他们似乎没有出现你这种问题 |
你好,我想请问一下levir-cd数据集我刚下载的时候里面的结构是test,trian,val,然后test里面的结构是A,B,Label,这个是正确的吗 |
@Sanfordhhhh please see the readme: https://github.com/ViTAE-Transformer/RSP/blob/main/Change%20Detection/README.md |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
作者您好!我在复现您的变化检测 LEVIR-CD 数据集部分内容时(BIT-ResNet50 训练,ResNet50 预训练模型使用torch官方结果),batch size设置为4 (大于4则会爆显存)。发现训练一个epoch需要十五分钟左右,这和 LEVIR-CD 较小的数据量不符。在复现 BIT 算法官方论文时,同样的模型设置训练一个 epoch 仅需一分钟,而且能接受更大(12)的 batch size 且不会爆显存。
希望咨询作者,这种情况发生的原因是什么?因为代码是在 BIT 基础上修改的,理论上不会有这么大的训练差距,所以非常疑惑。
非常期待作者的回复,谢谢!
The text was updated successfully, but these errors were encountered: