We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
您好,谢谢您的无私分享。我将crnn中的cnn结构替换成densenet结构时,遇到了一些问题。
solver文件设置test_initialization: true,TEST阶段的ctcloss=nan,accuarcy=0,一直到训练结束。 我打印训练日志看了下,TEST阶段连个LSTM层的输出均为nan,且bn层的参数值也不正常。
设置test_initialization: false时,1的问题就解决了,但是在模型训练好之后,利用模型对测试集进行评估时,准确率在45%左右;实际训练中训练集准确率=1, 验证集准确率为98%;我又用模型对验证集的准确率进行了统计,准确率也在55%左右。
这个问题一直困扰我很久,如果你也碰到了类似问题,请问有没有什么解决办法
The text was updated successfully, but these errors were encountered:
No branches or pull requests
您好,谢谢您的无私分享。我将crnn中的cnn结构替换成densenet结构时,遇到了一些问题。
solver文件设置test_initialization: true,TEST阶段的ctcloss=nan,accuarcy=0,一直到训练结束。
![image](https://user-images.githubusercontent.com/6924670/57360216-2de7f280-71ac-11e9-81d8-c3e4d50afd86.png)
我打印训练日志看了下,TEST阶段连个LSTM层的输出均为nan,且bn层的参数值也不正常。
设置test_initialization: false时,1的问题就解决了,但是在模型训练好之后,利用模型对测试集进行评估时,准确率在45%左右;实际训练中训练集准确率=1, 验证集准确率为98%;我又用模型对验证集的准确率进行了统计,准确率也在55%左右。
这个问题一直困扰我很久,如果你也碰到了类似问题,请问有没有什么解决办法
The text was updated successfully, but these errors were encountered: