Gchang9

> 请问是在运行什么任务的时候碰到的呢? 您好，代码位置在： flagai/mpu/local_attention_function.py from localAttention import (similar_forward, similar_backward, weighting_forward, weighting_backward_ori, weighting_backward_weight)

Dear Authors:： I also need your code to compare the experimental results. Thank you very much!My email address is [[email protected]]

> 您好，我尝试用您的代码训练的时候出现了如下问题。似乎是在计算loss的时候target应该是三维，但是debug进去发现label却还是四维，不知道该如何解决呢 > > Traceback (most recent call last): File "/data/yuanyifeng/Bi-SRNet-main/train_SCD.py", line 238, in main() File "/data/yuanyifeng/Bi-SRNet-main/train_SCD.py", line 65, in main train(train_loader, net, criterion, optimizer, scheduler, args, val_loader) File "/data/yuanyifeng/Bi-SRNet-main/train_SCD.py",...

似乎关闭Tensorboard就不会出现这个问题，请问是为什么呢？

关闭Tensorboard之后不会报warning，但训练几个epoch之后还是会出现train_seg loss bn_loss均为nan，想请问您一下是什么情况呢？

您好，由于我把近3000组图像划分为了训练、测试、验证。导致训练的时候最后一个batch不能整除。目前我把drop_last设置为True可以正常训练了。但Tensorboard的暂时还未发现解决方案、

Thank you, the loss function is nan because my batchsize is not divisible, I set Droplast to True and can train normally! There is actually a minor problem. I noticed...