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

docker version #3

Closed jakeoung closed 7 years ago

jakeoung commented 7 years ago

I have difficulty installing on my desktop. Also, if I run the demo based on caffe docker version, it has error something like:

Message type "caffe.LayerParameter" has no field named "augmentation_param"

My question is that is there any docker version that I can run?

wasidennis commented 7 years ago

Currently we do not have the docker version and will work on it.

The error you got is because the caffe image you use does not contain "augmentation_param". You would need to install the caffe contained in our repository.

jakeoung commented 7 years ago

Your reply helps me. I used the docker of FlowNet and finally can run your program. Thanks!

wasidennis commented 7 years ago

Thanks for your updates. Hope our work will benefit your study! Btw, could you also let us know which FlowNet docker image you use?