camvid weights question

[Jerry2990]

hi，thanks for your work and sharing.
i download the DDRNet_23_slim pre-trained weights on camvid datasets. However, it can't parse images and obtain accurate semantic segmentation results by normalize with mean_std = ([0.406, 0.456, 0.485], [0.225, 0.224, 0.229]) . Could you tell me how to evaluate with this model.
Thank you a lot!

PS:

[Dileepmeom]

I also have same issue, output tensor are no where close to the actual prediction. Anyone please suggest how to test the prediction with an actual image instead. Thank you

[ydhongHIT]

Hi, my CamVid dataloader is borrowed from DABNet. Hope this can help you.