About the Evaluation on Pascal Context

I noticed that you illustrate an example with Pascal Context dataset,

python test.py --dataset PContext --model-zoo Encnet_ResNet50_PContext --eval

pixAcc: 0.7838, mIoU: 0.4958: 100%|████████████████████████| 1276/1276 [46:31<00:00, 2.19s/it]

And I check your implementation and find that it seems that you compute the mIoU w/o considering the background classes.

Could you give me a guide about how to deal with the background class as our model is trained over 59 classes?

Thus I am wondering should we change line#19 within file "PyTorch-Encoding/encoding/datasets/pcontext.py"?

class ContextSegmentation(BaseDataset):
    BASE_DIR = 'VOCdevkit/VOC2010'
    # NUM_CLASS = 59
     NUM_CLASS = 60

Besides, I also notice that you pad zero during training, but such padding can introduce extra noises.

Start with the documented python test.py --dataset PContext --model-zoo Encnet_ResNet50_PContext --eval command and inspect PyTorch-Encoding/encoding/datasets/pcontext.py, especially NUM_CLASS. Compare how evaluation handles the background class with the model's 59 classes, then examine the zero padding used during training; done means the class-count and padding behavior are clearly resolved.