-
Notifications
You must be signed in to change notification settings - Fork 86
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
Cannot reproduce accuracy 84% (after step2) #11
Comments
Have you tried doing step-2 directly? |
@rohitgajawada yes, it gets even lower ~ 57% |
Oh that is sad, I also need a reproducible bilinear-cnn in pytorch. |
Never mind, saw issue #4 |
That's not a problem, since they compute a Gram matrix after Relu. Do you have any other good repository in mind? |
Ya my bad, realized it immediately after commenting :P If I find another repo that is able to reach the required accuracy, I'll notify you |
Hi @HaoMood , any updates with this problem? Were you able to obtain the 84% test accuracy? |
It is weird, since random seeds are fixed and I had tried it several times to make it can be re-implemented before this submission. Maybe you can give some details about your hardware, such as the GPU used as well as CUDA and cuDNN version. |
Hi Hao,
Thank you for a neat implementation.
I wonde if training with the hyperparameters written in README
gives 84.17% test accuracy?
I used exactly the commads which you provide in the README:
I have trained step1 model and got 76.67% accuracy on test. I use this as initialization for step2 model and finetune all the layers further. But the accuracy saturates at 76.61% and doesn't grow further.
Are there any extra tricks to get the desired performance?
The text was updated successfully, but these errors were encountered: