-
Notifications
You must be signed in to change notification settings - Fork 156
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
Found 2 (potential) bugs when training on semantic-only datasets. #75
Comments
Thanks Sebastian for your comment! We do not regularly use semantic segmentation, so we're always looking for feedback! Regarding your 2nd issue, I'd recommend to use a Regarding your 1st issue: Could you provide some more information on how you encoded the labels into tfrecords? If my understanding is correct, the issue is that you encode the image as a 3 channel image, but it's read out as 1 channel which leads to issues? Best, |
Regarding the 1st issue: |
Thank you for reporting the issue. Cheers, |
Thank you for your response, To be clear, the issue that I originally posted is currently not hindering me since I applied the fixes that I proposed above. I opened this issue to highlight 2 problems/bugs which might come up when a semantic-only dataset is used. |
Thank you for making this amazing work publicly available.
I am using deeplab2 with a semantic-only dataset, i.e. the red channel of the image contains the class label and the other channels are 0.
I followed the instructions, but found 2 issues that appear when using semantic-only datasets:
Issue 1
original:
proposed change:
The original code converts the image to grayscale instead of specifically selecting the red channel, which remaps the class labels.
Issue 2
original:
proposed change:
Only divide by the panoptic_label_divisor if the dataset is a panoptic dataset, otherwise the labels of a semantic-only dataset are overwritten.
Do you agree with me regarding these two issues?
The text was updated successfully, but these errors were encountered: