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

Is the evaluation correct for pascal segmentation ? #255

Open

pengwangucla opened this issue Mar 22, 2019 · 0 comments

pengwangucla commented Mar 22, 2019

Deformable-ConvNets/lib/dataset/pascal_voc.py

Line 367 in 81d3bd0

    
           seg_gt = cv2.resize(seg_gt, (seg_pred.shape[1], seg_pred.shape[0]), interpolation=cv2.INTER_NEAREST)

In this line you resize the ground truth label to the size of predicted label map, which may not be correct if the predicted scale varies.

Should it be resize prediction to ground truth label ?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment