how to train the dataset of us

sacmehta / ESPNet

ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

https://sacmehta.github.io/ESPNet/

MIT License

541 stars 112 forks source link

Closed zhangyunming closed 5 years ago

zhangyunming commented 5 years ago

hi, nice work , its the fastest i have seen ,

can u give a 'read me' about how to train our dataset.

maybe the input and class_num is difference and how to train the net from sctach

sacmehta commented 5 years ago

Training instructions for cityscapes should work for any dataset.

If your dataset has less than 20 classes, please see #13 .