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
请问目前2.0支持ppyolo,ppyoloV2 Anchor聚类方法,发现在ppyolov2_r50vd_dcn模型使用Anchor聚类方法V2,精度反而更差,默认的anchors反而精度更高
The text was updated successfully, but these errors were encountered:
您好,ppdet中ppyolov2 和 ppylo使用的anchor聚类方法是一样的,请问您说的两个聚类方法指的是ppdet中的聚类方法吗?请您再检查一下参数设置是否正确?训练时是否有其他参数不一样?
Sorry, something went wrong.
是一样的,参数是 v-n 9 -s 416 -m v5 -i 1000,会生成一个anchors,填入这个anchors精度还没默认的anchors精度高,训练时其它参数完全一模一样
No branches or pull requests
请问目前2.0支持ppyolo,ppyoloV2 Anchor聚类方法,发现在ppyolov2_r50vd_dcn模型使用Anchor聚类方法V2,精度反而更差,默认的anchors反而精度更高
The text was updated successfully, but these errors were encountered: