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.

Sign up for GitHub

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

Jump to bottom

Problems of training my own datasets #22

Closed

yangyuya opened this issue Aug 3, 2023 · 1 comment

yangyuya commented Aug 3, 2023

Hi, 作者您好

我之前尝试复现了RT-DETR_hgnet_l模型在COCO数据集上的结果，效果确实是会比yolov7更好！但是换成我自己的数据集（比较简单，只有两个类别）时会比yolov7低五个点左右，一直没找到原因。

我用的是这里单纯训练RT-DETR的代码，训练时加载了COCO上的预训练权重，一张卡batchsize=8，加了两倍的梯度累计，其他参数都没改。数据集是VOC格式的。

会是因为在这种简单数据集上更需要加mosaic之类的数据增广吗？
我看yolov7训练和测试时都是keep_ratio=True，这个会有影响吗？

期待您能给出一些提升mAP的建议~

Owner

lyuwenyu commented Aug 3, 2023

你可以把加了两倍的梯度累计关了就正常训练就行不用调LR
关于size的问题可以参考这里的一个长方形的做法 Train RT-DETR on custom data #4
数据是voc的格式那你eval的指标用的也是voc的嘛？

lyuwenyu closed this as completed

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment