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
您好,我在训练的时候发现mask-ratio原作者设置为4,您在issue里也提出了这个问题,请问您在训练的时候除了设置--mask-ratio 1以外,还修改了网络结构的那些部分?我只设置这个参数,但是验证的时候mAP很低
The text was updated successfully, but these errors were encountered:
Proto模块就是具体缩放系数的地方,最后上采样的次数就是反向缩放的系数,默认上采样1次,mask-ratio就是4,上采样两次就变成2,上采样3次就是1:1的比例。具体你可以自己尝试下修改这个模块相关。对比下效果。另外,这里的卷积如果不控制通道系数的话,计算量和参数量会很大,上采样次数越多越大。其他地方就要你自己研究了。
Sorry, something went wrong.
No branches or pull requests
您好,我在训练的时候发现mask-ratio原作者设置为4,您在issue里也提出了这个问题,请问您在训练的时候除了设置--mask-ratio 1以外,还修改了网络结构的那些部分?我只设置这个参数,但是验证的时候mAP很低
The text was updated successfully, but these errors were encountered: