Please could offer the pretrain model of Dnet? Thank you.

irfanICMLL / structure_knowledge_distillation

The official code for the paper 'Structured Knowledge Distillation for Semantic Segmentation'. (CVPR 2019 ORAL) and extension to other tasks.

BSD 2-Clause "Simplified" License

695 stars 104 forks source link

Please could offer the pretrain model of Dnet? Thank you. #6

Closed UrwLee closed 4 years ago

irfanICMLL commented 4 years ago

Hi, you do not need a Dnet for inference~ And you do not need a pre-train weight for Dnet if you want to train our model. Just follow the instruction and train a model with GAN end-to-end, you will get similar performance with us.