Video-friendly caffe -- comes with the most recent version of Caffe (as of Jan 2019), a video reader, 3D(ND) pooling layer, and an example training script for C3D network and UCF-101 data
I'm using the master branch (because I need the python wrapper to make python layers) and it works pretty well. Thank you for sharing your implementation!
But I'm not sure to understand how the convolution is performed over sequences. Can somebody explain to me how it works?
Hi,
I'm using the master branch (because I need the python wrapper to make python layers) and it works pretty well. Thank you for sharing your implementation!
But I'm not sure to understand how the convolution is performed over sequences. Can somebody explain to me how it works?