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/
Hi,
I was trying to train the crfasrnn model using the TVG_CRFRNN_new_traintest.prototxt and TVG_CRFRNN_new_solver.prototxt and i got an error(Note i have provided the lmdb files for both the labels and images for testing and training). I am using the pascal VOC 2012 dataset and for converting to lmdb i used data2lmdb.py from https://github.com/martinkersner/train-CRF-RNN. This was the error:
../../build/tools/caffe: symbol lookup error: /home/swamy/crfasrnn/caffe/.build_release/tools/../lib/libcaffe.so: undefined symbol: _ZTIN5boost6python15instance_holderE
Hi, I was trying to train the crfasrnn model using the TVG_CRFRNN_new_traintest.prototxt and TVG_CRFRNN_new_solver.prototxt and i got an error(Note i have provided the lmdb files for both the labels and images for testing and training). I am using the pascal VOC 2012 dataset and for converting to lmdb i used data2lmdb.py from https://github.com/martinkersner/train-CRF-RNN. This was the error:
../../build/tools/caffe: symbol lookup error: /home/swamy/crfasrnn/caffe/.build_release/tools/../lib/libcaffe.so: undefined symbol: _ZTIN5boost6python15instance_holderE
Please provide any insight you have. Thank you