In the DeepLabv3+ paper the authors state the following:
The proposed models are evaluated on the PASCAL VOC 2012 semantic segmentation benchmark [1] which contains 20 foreground object classes and one background class. The original dataset contains 1, 464 (train), 1, 449 (val), and 1, 456 (test) pixel-level annotated images. We augment the dataset by the extra annotations provided by [76], resulting in 10, 582 (trainaug) training images.
- What’s the exact PyTorch code to retrieve the trainaug dataset?
- The size of trainaug considers also the 1464 images of the PASCAL VOC 2012 dataset?
- What’s the exact code to retrieve the test dataset?