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.

Sign up for GitHub

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

Jump to bottom

BBOX issues #882

Closed
chexianghong opened this issue Jan 28, 2019 · 2 comments · May be fixed by #1401
Closed

BBOX issues #882

chexianghong opened this issue Jan 28, 2019 · 2 comments · May be fixed by #1401

Comments

@chexianghong
Copy link

Please make sure that you follow the steps below when creating an issue.
Only use GitHub issues for issues with the implementation, not for issues with specific datasets or general questions about functionality.
If your issue is an implementation question, please ask your question on the #keras-retinanet Slack channel instead of filing a GitHub issue.
You can find directions for the Slack channel here: https://github.com/fizyr/keras-retinanet#discussions

Thank you!

  1. Check that you are up-to-date with the master branch of keras-retinanet.
  2. Check that you are up-to-date with the latest version of Keras: https://github.com/keras-team/keras.
  3. Check that you are up-to-date with the latest version of TensorFlow.
    The installation instructions can be found here: https://www.tensorflow.org/get_started/os_setup.
  4. Check that you have read the entire README.md: https://github.com/fizyr/keras-retinanet/README.md.
    Most noticably the FAQ section shows common issues: https://github.com/fizyr/keras-retinanet#faq.
  5. Clearly describe the issues you're having including the expected behaviour, the actual behaviour
    and the steps required to trigger the issue.
  6. Include relevant output from the commands you're executing, including full stack traces where relevant.
  7. Remove this entire message and replace it with your issue.

I have debug my training samples by myself. When train the model using my own datasets, the issue is as below:
image
The bboxes are within the image. I do not know why it shows Image contains the following invalid boxes.
The bboxes are reasonable. Could you please give a explanation?
@hgaiser
Copy link
Contributor

hgaiser commented Jan 28, 2019

The shape is printed in numpy format: (rows, cols, channels), boxes are printed [x1, y1, x2, y2], so a box [73, 0, 211, 213] is outside of the range because 213 is higher than the number of rows 212.

Closing this as it is not an issue with the code. Please use the Slack channel for usage questions.

@hgaiser hgaiser closed this as completed Jan 28, 2019
@rafis
Copy link

rafis commented Jun 25, 2020

Why do limit bboxes to image boundaries? Why don't let model learn on those clamped photos treating them like occluded objects?

@rafis rafis mentioned this issue Jun 27, 2020
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Remove bboxes clipping rafis/keras-retinanet
3 participants
@hgaiser @rafis @chexianghong