Pyjcsx

Hi, please refer to issue https://github.com/jfzhang95/PoseAug/issues/43.

Hi, Did you use both voc and sbd datasets to train your model?

What is the backbone you used in your model? Actually I did not train the model on cityscapes dataset.

Yes, previous code miss bn after depth wise cnn. I have fixed it. But I do not have pretrained aligned xception model right now. So I dont recommend you use...

Hi, it is an error in `previous` branch, but in current branch, I have already fixed it.

Hi, I think you are right. When training model on cityscapes dataset, [mask](https://github.com/jfzhang95/pytorch-deeplab-xception/blob/b7cbf5a5ae8b3197ce9117f8fc64e0324bce4b3b/dataloaders/custom_transforms.py#L112) should be padded to 255 instead of 0. Otherwise it will affect final performance.

I tried to train ResNet based model on cityscapes dataset. My training setting is batch_size 16 (8 TITAN XP GPUs), base_size and crop_size 796, lr 0.01, epoch 200. Currently on...

Maybe you could explore [pytorch-encoding]( https://github.com/zhanghang1989/PyTorch-Encoding) or [drn]( https://github.com/fyu/drn) repos to try their training setting and data augmentation methods on Cityscapes dataset. I believe their code could help you.

Hi, all I just noticed an [issue](https://github.com/sacmehta/ESPNet/issues/9#issuecomment-392057816) in [ESPNet](https://github.com/sacmehta/ESPNet/). It seems like Cityscapes dataset script uses weighted mIoU. So maybe you can evaluate mIoU using the official script instead of...

It seems like the error is in your label. Maybe you should check your label, or you could provide more evidence about how this error comes up.