Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

损失很大 #50

Open
AishuaiYao opened this issue Apr 6, 2021 · 2 comments
Open

损失很大 #50

AishuaiYao opened this issue Apr 6, 2021 · 2 comments

Comments

@AishuaiYao
Copy link

我的损失很大,一般都在万以上,这样会不会造成梯度爆炸呢?
我的做法:

1 输入:下载了BSDBS500数据,使用原图和二值图标签训练,使用源代码中的方法,没有归一化输入,只是减每个通道均值
2 中间处理:模型超参数使用代码原始的参数,没有修改,batch 1 iter 10 lr 1-e6
3 输出:损失1w-2w,图相train文件夹里除了第一个有轮廓其他都是黑的或灰的,test文件夹下根本没有轮廓
希望有成功运行的人,能指点一下正确的处理过程,多谢!
1输入
2中间处理
3输出

@AishuaiYao
Copy link
Author

我解决了这个问题
1 输入:
wget http://mftp.mmcheng.net/liuyun/rcf/data/bsds_pascal_train_pair.lst
wget http://mftp.mmcheng.net/liuyun/rcf/data/HED-BSDS.tar.gz
下载后我截取了前3k个数据
2 中间:
使用代码原始参数,一些打印的参数可以改改,lr和iter和batchsize的都用原始的
3 输出:
损失开始从1k多几个epoch后到300左右,输出的轮廓图接近的样例了

@ForawardStar
Copy link

请问你最后F值是多少呢?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants