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.

Sign up for GitHub

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

Jump to bottom

复现精度与论文精度差距较大 #3

Open

weitaoO0 opened this issue Apr 14, 2023 · 1 comment

weitaoO0 commented Apr 14, 2023

我用pytorch对MCLDNN进行了复现，发现模型在高信噪比条件下的精度与原论文相差很大，只有70%多。
去掉最后两个LSTM层后反而达到85%左右的准确率。我的Batch size ，学习率，衰减方式等超参数均和原文一样，可是还是无法达到论文所展示的效果，这是为什么？

biubh commented Apr 20, 2023

我用pytorch对MCLDNN进行了复现，发现模型在高信噪比条件下的精度与原论文相差很大，只有70%多。去掉最后两个LSTM层后反而达到85%左右的准确率。我的Batch size ，学习率，衰减方式等超参数均和原文一样，可是还是无法达到论文所展示的效果，这是为什么？

你好，请问你解决上述问题了吗？或者有什么见解和意见吗？我也在做这个方向，如果方便的话可以给个联系方式讨论一下吗？

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment