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

how we can test or predict any image? #23

Closed
lisa676 opened this issue Sep 9, 2020 · 3 comments
Closed

how we can test or predict any image? #23

lisa676 opened this issue Sep 9, 2020 · 3 comments

Comments

@lisa676
Copy link

lisa676 commented Sep 9, 2020

Hi @Horea94 Thanks for this wonderful work. Training is ok but how I can test any image? Seems that there is no code for testing.

@Horea94
Copy link
Owner

Horea94 commented Sep 9, 2020

I added a test script under src/image_classification. This script is pretty straightforward, as it loads the saved model and makes a prediction on a single image.
If you want to test multiple images, I would recommend using a data generator. (Documentation)

@lisa676
Copy link
Author

lisa676 commented Sep 10, 2020

@Horea94 Thanks so much for this update. I run this file and its working fine. I'm getting result in terminal mode, how to save resultant image? I mean how to get predicted image with detected box around the object?

@Horea94
Copy link
Owner

Horea94 commented Sep 10, 2020

The model in this repo is a classifier. That is, it provides only a label prediction based on an input image.
For bounding box prediction, you would need a detector like Faster R-CNN, YOLO or SSD.

@Horea94 Horea94 closed this as completed Sep 14, 2020
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