search

JingchunCheng / SegFlow

Demo code of the paper "SegFlow: Joint Learning for Video Object Segmentation and Optical Flow", in ICCV 2017
178 stars 41 forks source link

caffe.LayerParameter has no field named "augmentation_param" #4

Closed nikepakou closed 7 years ago

nikepakou commented 7 years ago

Hi, Jingchun, when i run python infer_DAVIS.py dog, occured some error : [libprotobuf ERROR google/protobuf/text_format.cc:245] Error parsing text-format caffe.NetParameter: 4578:22: Message type "caffe.LayerParameter" has no field named "augmentation_param". F0925 20:41:47.197806 1821 upgrade_proto.cpp:88] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: ../model/deploy.prototxt Can you help me to slove this problem?

wasidennis commented 7 years ago

Have you installed the caffe contained in this repository? If yes, you should also include its pycaffe path (repository_path/caffe/python) in $PYTHONPATH. If you do both and still cannot install our caffe successfully, you may try to install the docker version of FlowNet that contains all required dependencies.

nikepakou commented 7 years ago

@wasidennis Thanks , I solved it . I installed caffe downloaded from https://github.com/BVLC/caffe , Are there some differents between caffe contained in this repository and BVLC/caffe ?