Confused about the F1-measure of ERFNet on CULane

cardwing / Codes-for-IntRA-KD

Inter-Region Affinity Distillation for Road Marking Segmentation (CVPR 2020)

MIT License

114 stars 24 forks source link

Confused about the F1-measure of ERFNet on CULane #15

Open byeciao opened 3 years ago

byeciao commented 3 years ago

The F1-measure of ERFNet on your paper is 70.2, but on ERFNet-CULane-PyTorch it is 73.1, even better than it with IntRA-KD. What's the difference between them?

cardwing commented 3 years ago

70.2 is the performance of ERFNet-Torch. Since ERFNet-PyTorch is even better than the teacher model, we have to take ERFNet-Torch as student.