Hi ,how can segment objects in output semantic image?

torrvision / crfasrnn

This repository contains the source code for the semantic image segmentation method described in the ICCV 2015 paper: Conditional Random Fields as Recurrent Neural Networks. http://crfasrnn.torr.vision/

Other

1.34k stars 462 forks source link

Hi ,how can segment objects in output semantic image? #108

Closed huihuangzhao closed 7 years ago

huihuangzhao commented 7 years ago

Hi , i can not install the crfasrnn into my computer , i just want to segment the object by using project website http://crfasrnn.torr.vision. i got a semantic image by using the website project. and i want to segment them. For example, i get a semantic image which has Chair, Bicycle ,and TV by the website project how can i change the chair's color to red(255,0,0), the bicycle's color to green(0,255,0), the TV's color to blue(0,0,255). Then i can segment them easily.

Thanks...

sadeepj commented 7 years ago

Hi huihuangz,

Our website http://crfasrnn.torr.vision is only for demonstration purposes. You would have to set up the CRF-RNN code on your own hardware to get the functionality you described.