摘要：
Do need to use model.eval() when I test? Sure, Dropout works as a regularization for preventing overfitting during training. It randomly zeros the ele 阅读全文
摘要：
参考： https://www.cnblogs.com/romangao/p/13052809.html https://blog.csdn.net/xie_0723/article/details/78004649 对于这样的文件结构： classfication #文件夹 │run.py ├─m 阅读全文