Skip to content
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

Problem about performance #36

Open
BrianWayland opened this issue Nov 18, 2020 · 3 comments
Open

Problem about performance #36

BrianWayland opened this issue Nov 18, 2020 · 3 comments

Comments

@BrianWayland
Copy link

BrianWayland commented Nov 18, 2020

As is shown in the result, the performance of trained model is very unsatisfying. Actually, after 100 epochs valid loss and train loss is so close, simply improving number of epoch can do nothing to performance. My problem is are there any solutions to promote the performance of the model?
route_03_gradient
route_04_gradient
route_05_gradient
route_06_gradient
route_07_gradient
loss

@knsjoon
Copy link

knsjoon commented Jan 17, 2021

@BrianWayland My valid loss is also very low but when I test them, I get very bad results as well.
Have you solved this issue?

@quanqhow
Copy link

quanqhow commented Jan 26, 2021

Hello, I also got the same bad result as shown below, so can anyone solve this problem?
route_04
route_05
route_07
route_09
route_10

@mariakalimeri
Copy link

I was not even able to reproduce these results. I trained a model with the same data and the loss definition and hyperparameters in the current commit, which seem to be the ones used to train the for the provided model in the README, but my results after 250 epochs are way worst than this.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants