ggsDing
使用BISRNRT作为Net训练模型时出现问题
您好，在使用SSCDl作为Net训练时，没有问题。在使用BiSRNet作为Net训练时，出现了问题，参数和数据及数据读取方式全部是按照您的代码做的。 出现的问题是： 训练的时候显示：WARNING:Nan or Inf found in Input tensor，且train_seg loss bn_loss均为nan
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、
Hi. Is the batch size too small? The BiSRNet is a bit hard to train but the loss shouldn't be crazy. I got accuracy improvements while freezing the other model parts and training only the SR modules. You can also try that.
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 that both the 'Models' folder and the main folder have a file named bisrnet.py, which defines the head layer, and the former does not. What is the purpose of these two? Thank you again!
在2022年5月23日 @.***> 写道：
Hi. Is the batch size too small? The BiSRNet is a bit hard to train but the loss shouldn't be crazy. I got accuracy improvements while freezing the other model parts and training only the SR modules. You can also try that.
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>