-
Notifications
You must be signed in to change notification settings - Fork 8
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
训练结果准确度无法提升问题请教? #3
Comments
1)经过多次重复实验,代码没有问题,请检查数据集或环境是否有误; |
同样的情况,训练数据集是Cars,第一个epoch是0.6%,30个epoch时准确率0.83%损失6.12基本不变化了,也是感觉没学习到,数据集检查过没问题,也用这个数据集训练过其他代码,请问您的问题解决了么? |
1)经过多次重复实验,代码没有问题,请检查数据集或环境是否有误; |
你好,我复现的时候准确率也是学习不上去,请问你解决了吗? |
训练了53个epoch,测试准确度还是只有0.39%,第1个epoch的时候准确度就是0.4多。说明真个训练网络都没有学习到。想问下我们这工程是论文官方的工程代码吗?是否能给出我们训练的结果?
训练数据使用bird,过程数据如下:
我觉得好奇的是我们网络为啥会丢掉一些卷积层的输出信息,位置如下Bottleneck:
The text was updated successfully, but these errors were encountered: