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

"FasterRCNN: 'OPA_FPN is not in the models registry'" #4

Open
Huzhen757 opened this issue Jul 5, 2021 · 2 comments
Open

"FasterRCNN: 'OPA_FPN is not in the models registry'" #4

Huzhen757 opened this issue Jul 5, 2021 · 2 comments

Comments

@Huzhen757
Copy link

Hello, I'm very interested in your work about FPN,but When I try to debug code,I using the image_demo script in the demo directory as well as using faster_rcnn_r50_opa_fpn_112_sml1_coco for config. However, it's report a error :
"FasterRCNN: 'OPA_FPN is not in the models registry'"

I have no idea,Hope you can give me a solution

@tingtingliangvs
Copy link
Collaborator

Thanks for your interest! Maybe you need to run python setup.py develop first. Please refer to install.md for installation and dataset preparation.

@Huzhen757
Copy link
Author

Thanks,I've solved this problem。
Now I want to ask, how to use the script in the code to debug. Because the image_demo script given in the source code, there are only have model initialization, image prediction and drawing prediction results.

I didn't find the implementation of preprocessing the input of a batch images, then model propagate and calculating loss.

In addition, README only gives the method of using .sh method to train as well as predict, and does not find how to call a script to debug the model. e.g. using one script of the source code to debug how does a batch image preprocess, propagate and compute loss?

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