-
The PASCAL VOC 2012 dataset we use is the commonly used 10582 training set version. If you don't already have that dataset, we refer you to Google or this blog.
-
Change the
PASCAL_ROOT
in configs/semantic_segmentation/common/datasets/_utils.py to your dataset's location.
├── <PASCAL_VOC.BASE_DIR>/VOCtrainval_11-May-2012/VOCdevkit/VOC2012
├── Annotations
├── ImageSets
│ ├── Segmentation
│ └── ...
├── JPEGImages
├── SegmentationClass
├── SegmentationClassAug
└── ...
More details are coming soon.