Closed Nine9Nine closed 6 years ago
Are you train from scratch, or using pre-train model? Maybe you can use smaller learning rate. It maybe related to your dataset distribution.
我是从零开始训练的,把weights路径注释掉了,学习率调了还是爆炸sad
Because of the network is deep and difficult to train, my suggestion is using a pre-training model. If you want to start training from scratch, you can freeze some layers during training.
多谢大佬
hello my lord, I convert the dataset to C version Yolo's format,the training process is smoothly.I think maybe something is wrong in your train program...
@Nine9Nine hello bro! I got the same problem, the loss is exploding to nan. How did you handle this problem? thanks a lot!
@ruikun 没解决,先用官网C版本对付了一下,之后还会继续研究
@Nine9Nine 你好,感谢回复,能不能麻烦你看一看我新开的帖里提出的问题? https://github.com/leeyoshinari/YOLO_v2/issues/7 帮忙给个思路,现在也不知道是train的方法有问题还是数据集的毛病。多谢!
I use your program to train my dataset(8 classes,2500pictures),the loss is too huge,should I change any parameters?