xuebinqin / U-2-Net

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
Apache License 2.0
8.66k stars 1.5k forks source link

How to train the human portrait drawing model? #345

Closed Harryoung closed 1 year ago

Harryoung commented 1 year ago

What confused me most is the training schema, i.e., in a segmentation way or a GAN way. In the original work, https://github.com/yiranran/APDrawingGAN, the model is trained in a GAN way. I wonder if the U-2-Net is trained in a segmentation way, i.e., directly predicts the sketch which is consisted of 0/1 pixels. Thanks!