How to implement netCLS when training on larger image size?

jhoffman / cycada_release

Code to accompany ICML 2018 paper

BSD 2-Clause "Simplified" License

561 stars 126 forks source link

How to implement netCLS when training on larger image size? #25

Open beerboaa opened 5 years ago

beerboaa commented 5 years ago

@jhoffman In cycle_gan_semantic_model.py, the netCLS was only implemented to work on digit datasets, how do I re-implement it for larger image resolution, say 256x256?