QianChen

hi，i have the same problem .i make the matcaffe and mattest successfully.but when i run the MSRnet,it was wrong ,this is my problem!hope your answer ustc115@ustc115:~/chenqian/code$ matlab -nosplash -nodesktop -r...

hey,can you tell me how to train in custom dataset?

yes,but the result it is not successful, so i give up At 2020-03-29 23:50:57, "lzzlxxlsz" wrote: have you run the code succssuffuly on your dataset? — You are receiving this...

no, i never test At 2020-04-02 14:48:09, "lzzlxxlsz" wrote: yes,but the result it is not successful, so i give up At 2020-03-29 23:50:57, "lzzlxxlsz" [email protected] wrote: have you run the...

Thank you for your attention and we will submit it within three days.

ok, the RD3D results of ReDWeb-S have been updated～

Yes, since we did not retrain the ReDWeb-S dataset and only tested it on this dataset with the previous model, this result is to be expected. At 2021-11-23 14:57:52, "fereenwong"...

pretrained weights? 在 2021-03-28 21:56:30，"吴晗" ***@***.***> 写道： — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.

simple resnet50 weights 在 2021-04-01 08:43:16，"吴晗" ***@***.***> 写道： pretrained weights? 在 2021-03-28 21:56:30，"吴晗" @.***> 写道： — You are receiving this because you are subscribed to this thread. Reply to this...

你好，感谢关注我们的项目，具体的训练参数在论文中均已提供，我们是用4张Titan Xp训练的，并非单张显卡。我们会在近期提供训练好的model。 在 2021-04-03 22:25:49，"llltttqq" ***@***.***> 写道： 作者你好，我这几天使用您提供的代码重新训练了好几次，我使用的是单张TitanXp，batch_size设为8（10的话显卡放不下），epochs=100，其他参数基本都使用您代码中的默认参数，最终训练loss都收敛到0.03左右，但测试效果都很不理想。所以我想请教一下您训练时的具体训练参数和最终loss收敛值是多少，最好能提供一下训练好的模型文件？ 万分感谢！ — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub,...