SimonVandenhende/Multi-Task-Learning-PyTorch

hrnet18+padnet

hanxuel opened this issue · 1 comments

hanxuel commented

Thank you very much for sharing the wonderful code! Your work is definitely very helpful for MTL community.

I am contacting you because I try to reproduce the result of hrnet18+padnet on nyud dataset. Literally

  1. downloaded the pretrain model of hrnet_w18_small_model_v2.pth
  2. python main.py --config_env configs/env.yml --config_exp configs/nyud/hrnet18/pad_net.yml
    But the performance is only Semantic Segmentation mIoU: 33.4665 depth 0.7267, not the result in your paper, do you have idea why is it?

Looking forward to hearing from you soon!
Thank you!

BanaBanaBanaa commented

Hi！ Have you solved this problem?
I met the same problem while I used the Pascal dataset.
The results of segmentation was 15.1530.