Guolei Sun

Hi, I think your code is fine. I looked it carefully, and I didn't find any problem. Did you reach the performance reported in the paper? Thanks a lot

Same problem. I also got ~75 mIOU using "train_voc.sh".

Same problem. I got 74.**% training on VOC2012 + SBD, and using Resnet. I can not get 78%. Seems that this code base is not good for reproduction.

I use "train_voc.py". Actually, I think my problem is exactly as the author of this issue. But the issue seems not solved.

Basically, what I want to do is to reproduce "78.43%" using "train_voc.py". Of course, I prepared for SBD dataset and train the model on VOC2012 + SBD. But I only...

Hi guys, For those who want to reproduce results on deeplab V3, I recommend this code: https://github.com/chenxi116/DeepLabv3.pytorch The code can simply reproduce 76.8% mIOU in Pascal val (trained on VOC2012...

@DL-ljw @tsing-cv @yangxue0827 have you guys solved this problem? Thanks.

Same problem, could you please reply?

Hi, do you reproduce the results on face verification?

Thanks for your interest. Initially, we did not release the configs and pre-trained weights for cityscapes because video data of cityscapes is extremely large (>300 GB). Nevertheless, we will release...