Luodian / MADAN

Pytorch Code release for our NeurIPS paper "Multi-source Domain Adaptation for Semantic Segmentation"
https://arxiv.org/abs/1910.12181
MIT License
170 stars 27 forks source link

the proper weight of the semantic loss #4

Open dannybarash7 opened 4 years ago

dannybarash7 commented 4 years ago

Hi,

the training script scripts/CycleGAN/cyclegan_gtasynthia2cityscapes.sh contains:  --DSC --DSCweight 20,  but the python main() doesn't accept "DSC" parameters and it fails. 

But, a semantic weight of 0.2 as default, appears in base_options.py:  _self.parser.add_argument('--general_semanticweight', type=float, default=0.2, help='weight for semantic loss')

Which one is the correct one?

TIA