Chuong Huynh

Can you create a new branch and then I can create a pull request to that branch?

Please give more information about the error

To train the backbone, you are suggested to run on big GPUs (from previous works). I used V100 32GB. To train the refinement module, I used 2080Ti 11GB. However, you...

Hi, The results in Table 8 are performed with the multi-scale/ flipping setting adopting from the [GLNet](https://github.com/VITA-Group/GLNet) paper for a fair comparison. Unfortunately, that testing script is not included in...

Hi, Sorry, it's not multi-scale, it's flipping/rotating testing. You can check the code here https://github.com/VITA-Group/GLNet/blob/7b7bdee196e368a1f3a32c54b984915f8e397275/helper.py#L434

Hi, there is an overlapping between patches. You can use the code I provide to get 64 patches

Hi, There are two separate sections: one for backbone training, one for refinement module training. Please check that, currently the two modules can not be joint trained.

That's the input size of the Cityscapes. You can run on your own images but you need to make sure that all configs (patch size, scales) are reasonable.

Can you give me the script you were running?

Hi, The first two lines are the final IoU while the last line is the IoU of a single image (and in this case, this is the last image). There...