README.md

Data Preparation

Download GTA5, Cityscapes, IDD, Mapillary

We adopt Class uniform sampling proposed in this paper to handle class imbalance problems. GTAVUniform and CityscapesUniform are the datasets to which Class Uniform Sampling is applied.

We used GTAV_Split to split GTAV dataset into training/validation/test set. Please refer the txt files in split_data.

You should modify the path in "<path_to_robustnet>/config.py" according to your dataset path.

#Cityscapes Dir Location
__C.DATASET.CITYSCAPES_DIR = <YOUR_CITYSCAPES_PATH>
#IDD Dataset Dir Location
__C.DATASET.IDD_DIR = <YOUR_IDD_PATH>
#Mapillary Dataset Dir Location
__C.DATASET.MAPILLARY_DIR = <YOUR_MAPILLARY_PATH>
#GTAV Dataset Dir Location
__C.DATASET.GTAV_DIR = <YOUR_GTAV_PATH>

Folder Structure of Datasets

You can set dataset roots in config.py.

├── data
      ├── GTA5
            ├── images
                  ├── train
                         ├── 01
                         ├── 02
                         ├── ...
            ├── labels
                  ├── train
                         ├── 01
                         ├── 02
                         ├── ...
      ├── Cityscapes
            ├── leftImg8bit_trainvaltest
                  ├── leftImg8bit
                         ├── train
                         ├── val
            ├── gtFine_trainvaltest
                  ├── gtFine
                         ├── train
                         ├── val
      ├── IDD
            ├── leftImg8bit_trainvaltest
                  ├── leftImg8bit
                         ├── train
                         ├── val
            ├── gtFine_trainvaltest
                  ├── gtFine
                         ├── train
                         ├── val
      ├── mapillary
            ├── training
                   ├── images
                   ├── labels
            ├── validation
                   ├── images
                   ├── labels