Mrlong12

And in the NJU2000 dataset ,the result you gave only has 485 images like that:  but other paper has 503 images like that 

or can you give me the three dataset?

thank you！when I look at your code , I do not know your total loss how to calculate.how many are the weights of three loss, when you calculate the total...

Thanks

And if I want to use the loss to train other task?such as the Semantic segmentation or saliency detection,the mask I should set 0.but how can i set the bin...

thanks , I will be try it.