crack_segmentation icon indicating copy to clipboard operation
crack_segmentation copied to clipboard

Published 20 hours ago • verified publisher icon khanhha

the pretrained weight of resnet is invalid

Open KangchengLiu opened this issue 6 years ago • 6 comments

I want to cite your work on github in my paper related to UAV bridge inspection, but the weight of the pretrained weight of resnet is invalid, please check it on your github so that I can cite your work, thanks!

KangchengLiu avatar Jul 07 '19 09:07 KangchengLiu

hello, sorry for the late response. I accidentally deleted the model from my drive. Working on retraining resnet23 and will upload the weight in two days

khanhha avatar Jul 07 '19 13:07 khanhha

I would be interested in this as well. Were you able to retrain your model? Thanks for providing this repo.

stvogel avatar Jul 23 '19 19:07 stvogel

@khanhha have you found the time to re-train the model yet? would be awesome to try it out.

gitunit avatar Sep 15 '19 11:09 gitunit

@khanhha ping

gitunit avatar Sep 30 '19 22:09 gitunit

@gitunit : hello. Sorry. I am too busy at work. You might have to train resnet yourself. But the accuracy from Resnet is not much higher than VGG16.

khanhha avatar Oct 01 '19 06:10 khanhha

@khanhha Is there an error in the results table? You reported that Unet+Resnet has better performance however it seems the IoU is higher for VGG.

alono88 avatar Nov 14 '19 19:11 alono88