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

Custom Training and testing #1

Open
Ehteshamciitwah opened this issue Jan 8, 2024 · 1 comment
Open

Custom Training and testing #1

Ehteshamciitwah opened this issue Jan 8, 2024 · 1 comment

Comments

@Ehteshamciitwah
Copy link

Hello, Thank you for sharing the code. I am using your code for the classification of my custom data. The image size of the dataset is just 64x64 and has 8 classes.
I just want to know, if can you provide the testing code so one can test the final checkpoint and calculate the confusion matrix. Thank you

@kamrul-NSL
Copy link

After completing the training best_checkpoint.bin file will saved as checkpoint. Please check the training script train.py file and it's 214, 215 line. Just use the test data instead of training data and then remove the comment from 214 and 215 line. Then it will load the best_checkpoint file and perform test. You can do it outside the epoch_iterator also by adding these two lines. Thanks.

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

2 participants