huhu

have you give the script?i want to train your code with CHIP dataset

i have also the problem , how ?

@YAwei666 NO , have not

have you solved? the same question.@pantingchn

the bug is ok.its similar with pytorch-unet

Almost all the test images are foreground..


Yes，when i do everything same with issue50，its still the problem

hi, i use this demo.py modified by the demo.ipynb, it can run and return teh result ,but the result is all wrong。 the code is： #!/usr/bin/env python # -*- coding:...

yes the reson is the code is in python3 but run python2 istead：super(ICNet_BN,self).__init__(inputs={'data': self.images}, cfg=self.cfg) may work