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
您好,我使用相同的代码训练以ResNet22W为骨干网络的SiamFC模型,使用相同的超参数,50个epoch中,在OTB100数据集上,性能最好的那一组结果是
| SiamDWE5 | 0.649 | 0.000 | 0.862 |,始终无法到达0.671,
请问您的网络训练过程中有什么其他技巧,或者超参寻找的时候有一些什么技巧吗?
—
Reply to this email directly, view it on GitHub
<#119>, or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AF6U2PGJF2LGJ3AMKZVF3CLXOYVMBANCNFSM6AAAAAAZ7YWPYE>
.
You are receiving this because you are subscribed to this thread.Message
ID: ***@***.***>
--
From: Zhang Zhipeng
Institution: National Laboratory of Pattern Recognition
Address: 95 Zhongguancun East Road, 100190, BEIJING, CHINA
Email: ***@***.***
Best Wishes
您好,我使用相同的代码训练以ResNet22W为骨干网络的SiamFC模型,使用相同的超参数,50个epoch中,在OTB100数据集上,性能最好的那一组结果是 | SiamDWE5 | 0.649 | 0.000 | 0.862 |,始终无法到达0.671, 请问您的网络训练过程中有什么其他技巧,或者超参寻找的时候有一些什么技巧吗?
The text was updated successfully, but these errors were encountered: