Boye

Have you already solve this problem？ I meet this problem too。— —！

@dangz90 I have been stuck in this problem for a week, could you please send the right answer to [email protected],if you have solved this problem .Thank you very much.

Also waiting for the code. Thanks

@asa008 Do you solve the problem？

Hi @jbeomlee93 ! I tried to reproduce "SEAM+AdvCAM" by myself but only achieved 50.96mIoU. I think the difference (50.96 vs 58.6) was caused by my wrong experimental setting. I used...

@jbeomlee93 Thanks for you reply. I will try it again.

@jbeomlee93 Since the CAM output of SEAM has 21 classes (20 classes + background), the default class label for your adv_cam is 20. So you also attck the background On...

Hi @jbeomlee93 Thanks for your reply. I have followed your suggestion in #7 (comment), #8 (comment) and retrained the "SEAM+Adv_cam". But the performance is even worse. I have changed 4...

您好，感谢关注，理论上多卡同步训练的训练结果不会差于单卡，我们也没有用多卡训练过，不好意思。 ---- 回复的原邮件 ---- | 发件人 | ***@***.***> | | 日期 | 2023年04月07日 11:04 | | 收件人 | ***@***.***> | | 抄送至 | ***@***.***> | | 主题 | [YeRen123455/Infrared-Small-Target-Detection] 关于多GPU训练的问题...

需要再运行测试函数