search

VITA-Group / FasterSeg

[ICLR 2020] "FasterSeg: Searching for Faster Real-time Semantic Segmentation" by Wuyang Chen, Xinyu Gong, Xianming Liu, Qian Zhang, Yuan Li, Zhangyang Wang
MIT License
526 stars 107 forks source link

How to prepare the training dataset from custom dataset #44

Closed rose-jinyang closed 4 years ago

rose-jinyang commented 4 years ago

Hello How are you? Thanks for contributing this project. I am going to train a new model with my custom dataset (supervisely-person-dataset). How should I prepare the training dataset? Thanks

chenwydj commented 4 years ago

Hi @rose-jinyang! Thank you for your interest in our work!

To train on your own dataset:

  1. Prepare your RGB images and ground truth label (for file format please refer to Cityscapes).
  2. Prepare file name lists as "dataset files" for data loading (see examples here).
  3. Change num_classes to the semantic classes in your data (in configuration file).