Open jthsieh opened 6 years ago
I have tried the GCN method on the gtFine dataset ,and get m_IOU=67 % on cityscapes. Have you reproduced the performance on the cityscapes reported by the paper ?
I managed to run FRRN A with this code https://github.com/meetshah1995/pytorch-semseg and achieved the reported mIoU. I used the exact hyperparameters reported in the FRRN paper.
Hi, would anyone be kind enough to share the results? Having trouble while getting the results too
Thank you for your awesome code! I've been trying to run some models on Cityscapes including FCN8, PSPNet and DUC, but I haven't been able to replicate the results reported in the papers. So if it's not too much trouble, can you please provide the results you got when testing your models. Thank you so much!!