We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
使用s3dis area1作为验证集,在linux和windows上训练100次后miou不到20%,重复训练很多次了都提不上去,为什么?环境:linux/windows,tensorflow-gpu=2.6,nvidia 1065-ti 4g内存,batchsize=1
The text was updated successfully, but these errors were encountered:
RandLA-Net模型在bach_size=1的时候会产生过拟合现象。所以要确保bach_size>=2,此时可以降低num_points来解决GPU内存不足的问题。 另外RandLA-Net模型可以在windows和ubuntu下运行,需要注意的是在windows下运行时”最近邻搜索knn_search“的结果错误的,需要 参考 原作者代码后面的回复 或者 参考Open3D实现RandLA-Net模型的代码 来解决。再次感谢博主的工作!
Sorry, something went wrong.
什么意思啊
@gxushine 我们能添加一个联系方式吗,想向你请教几个问题,关于环境的,希望能得到你的帮助 QQ:1589312910
No branches or pull requests
使用s3dis area1作为验证集,在linux和windows上训练100次后miou不到20%,重复训练很多次了都提不上去,为什么?环境:linux/windows,tensorflow-gpu=2.6,nvidia 1065-ti 4g内存,batchsize=1
The text was updated successfully, but these errors were encountered: