search

MPI-IS / bilateralNN

Learning Sparse High Dimensional Filters with Neural Networks
http://bilateralnn.is.tue.mpg.de
BSD 3-Clause "New" or "Revised" License
69 stars 25 forks source link

Accessing the Permutohedral Layer to define a Net through Python Code #8

Closed codepujan closed 7 years ago

codepujan commented 7 years ago

I am designing my Caffe Net through python . Just like Importing any other Caffe Layers , is there any way we can import the Permutohedral layer in Python Code .

Thank you !!

varunjampani commented 7 years ago

Yes, you can use pycaffe to specify any layer in caffe, including 'permutohedral' layer. We used this layer for propagating information across video frames. You can find an example net specification with permutohedral layers here: https://github.com/varunjampani/video_prop_networks/blob/master/seg_propagation/create_online_net.py