search

xiaoyufenfei / LEDNet

LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
https://github.com/xiaoyufenfei/LEDNet
MIT License
514 stars 79 forks source link

training data #21

Closed jhch1995 closed 4 years ago

jhch1995 commented 4 years ago

Thank you for your contribution. Can you give more details about training on VOC dataset? I think the number class on VOC dataset is 21(background + other category labels).

xiaoyufenfei commented 4 years ago

Hi! I don't have a model trained in VOC dataset since the focus of my research are road scenarios like Cityscapes、Camvid. However it would be easy to add a dataset loader in the code for VOC and test with it.