search

AngeLouCN / CaraNet

Context Axial Reverse Attention Network for Small Medical Objects Segmentation
462 stars 30 forks source link

binary segmentation #18

Closed aram200 closed 2 years ago

aram200 commented 2 years ago

Hi, thank you for sharing your code. it is really helpful for me

anyway, i have a question. I tried applying your code to my data. My data label values consist of 0,1 . When applied to this code, the output is 0-255. Can you tell me which part needs to be modified to adjust the output value to 0 and 1? I will wait for your reply. thank you

AngeLouCN commented 2 years ago

Hi, thank you for your interest.

I think everything is fine in the Train.py file. In the Test.py, I use misc.imsave function (line 67) to save the output. It automatically convert a [0, 1] output to [0, 255]. Maybe you can change some other save function or divide 255 for output.

aram200 commented 2 years ago

thanks alot