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

Getting Object Labels #59

Closed
goyalsaransh97 opened this issue May 23, 2019 · 3 comments
Closed

Getting Object Labels #59

goyalsaransh97 opened this issue May 23, 2019 · 3 comments
Labels
enhancement New feature or request

Comments

@goyalsaransh97
Copy link

Is there a way for getting the object labels for bounding boxes, given by the (fine-tuned) Detectron model?

@apsdehal
Copy link
Contributor

apsdehal commented May 23, 2019

Currently, we don't have this data present in our object features. You can check Colab demo to understand how to extract object features and every other information at your end. You can also look into maskrcnn-benchmark for extracting object features.

For TextVQA, we have some information including bounding boxes coordinates and other stuff in info files but it still doesn't contain object labels. We probably won't be supporting this in near future.

@goyalsaransh97
Copy link
Author

Precisely which model(and version) are you using for object detection?

@apsdehal apsdehal added the enhancement New feature or request label Jun 1, 2019
@apsdehal
Copy link
Contributor

apsdehal commented Jun 4, 2019

You can use the script here and follow the instructions to install. Comment out the lines to get all the relevant data other than features:
https://github.com/facebookresearch/pythia/blob/master/tools/extract_features.py#L190-L198

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants