当我使用交叉熵loss进行训练我的自定义数据集时，出现了loss不下降的问题（During the training of my custom dataset using cross-entropy loss, I encountered the issue of the loss not decreasing）

[jiaweichaojwc]

感谢大佬非常优秀的工作 当我使用交叉熵loss进行训练时，loss一直不下降，而且mIoU一直是7左右，不知道有没有什么解决办法 Thank you for the compliment. When I train using cross-entropy loss, the loss consistently does not decrease, and the mIoU (mean Intersection over Union) remains around 7. I'm not sure if there is a solution to this issue."