The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
8.31k
stars
1.43k
forks
source link
u2net for semantic segmentation #382
Open
fhfeishi opened 2 months ago
如果说 model = unet_full(out_ch=3), 2类目标+背景 我应该如何修改， cross-entropy loss一直是0