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

The model testing accuracy is very low #1

Open
aonrdbit opened this issue May 10, 2022 · 0 comments
Open

The model testing accuracy is very low #1

aonrdbit opened this issue May 10, 2022 · 0 comments

Comments

@aonrdbit
Copy link

Hello, have you tested the accuracy of the model under this PS structure?

When I used cifar10 dataset to train the resnet18 model, the accuracy of trainset was normal, but the accuracy of the testset was about 10%, that is to say, the model had no effect.

This is because model.eval() is used during testing.

But I don't know why. Can you help me explain why? I would appreciate it if I could receive your reply.

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

1 participant