search

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 460 forks source link

retraining #126

Closed gopi77 closed 7 years ago

gopi77 commented 7 years ago

Hi Instead of downloading TVG_CRFRNN_COCO_VOC.caffemodel, i would like to generate it by retraining.

  1. Do I need to write any new code?
  2. Also please provide me the datasets used &
  3. training steps in detail (python command line details preferred)

Regards Gopi. J

sadeepj commented 7 years ago

Please refer to our paper http://www.robots.ox.ac.uk/~szheng/papers/CRFasRNN.pdf for the details of the datasets/training procedure.