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

Why do we have resizedimagesfolder here ? #12

Open
akashjain0207 opened this issue Jul 15, 2020 · 1 comment
Open

Why do we have resizedimagesfolder here ? #12

akashjain0207 opened this issue Jul 15, 2020 · 1 comment

Comments

@akashjain0207
Copy link

This is not an issue but curious to know why do we have resizedimages folder. Code worked fine without that folder too.
But if I have to use this code on my own dataset, can I resize it first and run the trainer to save time ? Will the accuracy be same ?

@harry418
Copy link

harry418 commented Aug 5, 2020

Resized image is used for Machine learning and Deep learning models. These model takes input image with same size on which model is trained. If you are not Detecting or predicting anything ,then it is not necessary to resize image.

Other method is you can resize image using for loop and cv2.resize function. no need to save image in a folder.

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