Closed ghost closed 4 years ago
Hi,
when executing
python train.py --evaluate --snapshot checkpoints/best_cityscapes_checkpoint.pth
I achieve a slightly better IoU value than in your arxiv paper. Is the arxiv paper not up-to-date or is this a bug?
Yep, our released model is slightly better than what we initially report in the paper. This not a bug.
Hi,
when executing
python train.py --evaluate --snapshot checkpoints/best_cityscapes_checkpoint.pth
I achieve a slightly better IoU value than in your arxiv paper. Is the arxiv paper not up-to-date or is this a bug?