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.

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

I use mixmatch to train my own data set, which is simpler than cifar10 image. After running several epoch, the loss function of training and trainstats will become larger, and the accuracy of test set will be reduced #36

Open
ghost opened this issue Dec 9, 2020 · 3 comments
Open

I use mixmatch to train my own data set, which is simpler than cifar10 image. After running several epoch, the loss function of training and trainstats will become larger, and the accuracy of test set will be reduced #36

ghost opened this issue Dec 9, 2020 · 3 comments

Comments

@ghost
Copy link

ghost commented Dec 9, 2020 •
edited by ghost
Loading

No description provided.

@ghost ghost changed the title I use from progress.bar Import bar as bar. The program will run normally, but no progress bar will be output I use mixmatch to train my own data set, which is simpler than cifar10 image. Why is the accuracy of training set rising while that of test set declining? Dec 9, 2020
@ghost ghost changed the title I use mixmatch to train my own data set, which is simpler than cifar10 image. Why is the accuracy of training set rising while that of test set declining? I use mixmatch to train my own data set, which is simpler than cifar10 image. After running several epoch, the loss function of training and trainste will become larger, and the accuracy of test set will be reduced Dec 10, 2020
@ghost ghost changed the title I use mixmatch to train my own data set, which is simpler than cifar10 image. After running several epoch, the loss function of training and trainste will become larger, and the accuracy of test set will be reduced I use mixmatch to train my own data set, which is simpler than cifar10 image. After running several epoch, the loss function of training and trainstats will become larger, and the accuracy of test set will be reduced Dec 10, 2020
@ghost
Copy link

ghost commented Jan 3, 2021

I face the same question : the loss of train becomes smaller , but the loss of val becomes larger.
My own dataset has 200 classes

@Lotk1103
Copy link

Lotk1103 commented Jan 7, 2022

I face the same question : the loss of train becomes smaller , but the loss of val becomes larger. My own dataset has 200 classes

Hey, do you solve this problem? I meet the same question, is it realted to dataset imbalance?

@SuperJunier666
Copy link

我也遇见了这个问题，我是用这个方法做分割

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@SuperJunier666 @Lotk1103