search

bigmb / Unet-Segmentation-Pytorch-Nest-of-Unets

Implementation of different kinds of Unet Models for Image Segmentation - Unet , RCNN-Unet, Attention Unet, RCNN-Attention Unet, Nested Unet
MIT License
1.87k stars 345 forks source link

The color of label and a suggestion #38

Closed xumeng19 closed 4 years ago

xumeng19 commented 4 years ago

Hello, the author, first of all, thank you very much for the code. Excuse me, the label of the picture I input is binary. Why is the predicted picture not binary? Where do I need to change the color of the forecast picture? There is also a small suggestion, can you make the code more readable?

bigmb commented 4 years ago

It just had more channels. Try to visualize each channel, and you will get your required output. I think there will be a 4 channel prediction image.

If you have some help in understanding the code just let me know. I did try to comment on it at that time. But to restructure it will take some time and I have other commitments right now. Also if you do it, then I will be happy to merge and give you the credits.

xumeng19 commented 4 years ago

I'm sorry, I'm just a beginner. Thank you very much for your answer, but I can't help you with my ability

ppjerry commented 4 years ago

import skimage.io as io using io.imsave instead of the plot.imsave when saving images

xumeng19 commented 4 years ago

保存图像时，使用io.imsave而不是plot.imsave将skimage.io作为io导入

OK, thank you. I'll try