How to generate 'image_x' in test_data.pkl?

[Frank-Dz]

Hi~ I ran PGN on my cropped image: and got segmentation result: 023622.mat 023622.png 023622_vis.png

The following is 023622_vis.png:

The following is 023622.mat:

Then how can we build data in the test_data.pkl for image_0 (suppose this is the firt image)? Since I noticed that the image_x in test_data.pkl is

The color is quite different from the PGN one.

Thanks again!

Best, Frank

[neonb88]

Hi,

I appreciate your willingness to ask questions whenever you are stuck. Some people are too proud to do that. I can send you some code I used to fix some of these issues, but please be patient. I will not do it right now; maybe tomorrow. E-mail me at neonb88@yahoo.com and I can send you my cell phone number. Happy to collaborate

Cheers, Nathan

[neonb88]

You can find all the values of the colors, though, and set them equal to other values. It's something like:

WHITE = [255, 255, 255]
hair_red_color= [255,0,0]
img [ np.where(img==hair_red_color)   ] = WHITE

[hy-i-hairy]

但是，您可以找到所有颜色值，并将它们设置为与其他值相同。就像这样：

WHITE = [255, 255, 255]
hair_red_color= [255,0,0]
img [ np.where(img==hair_red_color)   ] = WHITE

Hello, I'm sorry for the sudden interruption. I would like to ask how long sleeves and short sleeves or trousers and shorts are marked in different colors? Looking forward to your reply.Thank you