Weights

[chunweit]

@moothes May I know what is the purpose of having these weights = [0.1, 0.3, 0.5, 0.7, 0.9, 1.5] in Loader.py? How those weights are determined?

[moothes]

There are 5 saliency and 5 contour supervision in our decoder. So the first 5 weights are used to weight these intermediate supervision. The final 1.5 is the weight of the final prediction.