Pilhyeon
How to reproduce the GTEA
Is there any trick to reproduce the result of GTEA , could you please giving config.txt for this dataset and it will be convenient for reproducing. Thank you.@Pilhyeon
Hello, I provide some hyper-parameter settings for GTEA below.
batch_size: 7 feature_fps: 15 search_freq: 1 budget: 200 lambdas: [1, 1, 1, 1, 1]
Hope this would be helpful. Best regards.
the result I reproduce is about 40.83mAP on GTEA, there is still some gap.
请问作者给了参数后你复现出原来的结果了吗？
the result I reproduce is about 40.83mAP on GTEA, there is still some gap.
请问作者给了参数后你复现出原来的结果了吗？
现在没做这个了，你试过了吗
@Pilhyeon Hello, can you provide some hyper-parameter settings for BEOID? Thanks!
the result I reproduce is about 40.83mAP on GTEA, there is still some gap.
请问作者给了参数后你复现出原来的结果了吗？
现在没做这个了，你试过了吗
the result I reproduce is about 40.83mAP on GTEA, there is still some gap.
能分享一下你复原的代码吗，我想试试能不能复现一下，感谢！
您好！由于使用作者提供的参数仍然无法复现其结果，已经中断该实验了。
------------------ 原始邮件 ------------------ 发件人: "Pilhyeon/Learning-Action-Completeness-from-Points" @.>; 发送时间: 2023年4月2日(星期天) 晚上6:52 @.>; @.@.>; 主题: Re: [Pilhyeon/Learning-Action-Completeness-from-Points] How to reproduce the GTEA (Issue #5)
the result I reproduce is about 40.83mAP on GTEA, there is still some gap.
请问作者给了参数后你复现出原来的结果了吗？
现在没做这个了，你试过了吗
the result I reproduce is about 40.83mAP on GTEA, there is still some gap.
能分享一下你复原的代码吗，我想试试能不能复现一下，感谢！
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>
