-
Notifications
You must be signed in to change notification settings - Fork 0
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
Low accuracy #1
Comments
Hey @chih3b , thank you for your interest in the project,yes there are a couple of ways to improve it. Previously I was just loading all the images into memory and that's why it ran out of RAM, this can be fixed by utilizing Generators instead |
Thanks for responding,can you explain how to do that please? |
Okay generators help to minimize if not to get rid of potentially running out of memory when working with bulky data. They only retrieve data from storage that is to be used. There are a couple of tutorials on how to import data using generators [https://towardsdatascience.com/keras-data-generators-and-how-to-use-them-b69129ed779c](Checkout this Article). All this generators here will definitely help to avoid the issue of running out of RAM |
Thank you so much.You really saved a lot of time for me.If it is possible can you u update the project to implement these generators or other methods to limit out of memory error? |
I will look into it and see |
Thank you.waiting for updates😁 |
did you find a solution bro?i really need this project.it would be a great favor if you help me with it. |
Hello,first of all thank you for providing this amazing project,You helped me a lot.But,the accuracy is very bad,is there a way to pass the ram limit in kaggle or something?
The text was updated successfully, but these errors were encountered: