You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
你好,我使用自己的训练集(只有1类物体)进行train from scratch ,但是训练的过程中,top1和top2始终是1.0000(eval也是这样的),如图所示:
使用的配置文件为resnet50_vd.yaml,在配置文件中我改了类别数为2,请问这种情况应该怎末更改配置文件?还有一个问题是,如何拿PaddleClas训练完成的分类模型使用PaddleDetection进行目标检测?谢谢!
The text was updated successfully, but these errors were encountered:
你好,我使用自己的训练集(只有1类物体)进行train from scratch ,但是训练的过程中,top1和top2始终是1.0000(eval也是这样的),如图所示:
使用的配置文件为resnet50_vd.yaml,在配置文件中我改了类别数为2,请问这种情况应该怎末更改配置文件?还有一个问题是,如何拿PaddleClas训练完成的分类模型使用PaddleDetection进行目标检测?谢谢!
The text was updated successfully, but these errors were encountered: