-
Notifications
You must be signed in to change notification settings - Fork 4
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
Performance Benchmarks #37
Comments
How much is the overhead compared to other regularization methods, and how fast is the trained forward methods afterwards? Those are the two factors to understand. Let's get @jessebet on here to start discussing as well. |
Updated the pdf with the FFJORD results on the gaussian dataset:
The MNIST classification shows similar trend with a reduced training time when the tolerance is low. At lower tolerance, the training timing is slower. The overall inference time is still lower than unregularized one. |
Regarding performance comparisons with other methods. The papers report GPU training times, but currently I am not being able to get the regularization to work on GPUs #42. Once jacobjinkelly/easy-neural-ode#2 gets fixed, I can run these on CPU and measure the performance. |
Proper Benchmarks available in the paper |
When using regularization, the training doesn't scale very well with the increase in batch size:
All the benchmarks use the models from here and use Tracker.jl
The text was updated successfully, but these errors were encountered: