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
My training data is a sequence,and label is an image. I'm not good at C++. To use Nd
convolution layer, is it possible to write a python data layer as input ??
If possible, What is the shape of output array in python data layer ??
Thank you.
My training data is a sequence,and label is an image. I'm not good at C++. To use Nd convolution layer, is it possible to write a python data layer as input ?? If possible, What is the shape of output array in python data layer ?? Thank you.