This is an implementation of the paper Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution. Works with version 1.0.
gan3sh500/octaveconv-pytorch
Implementation of Octave Convolution from Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution in Pytorch (https://arxiv.org/abs/1904.05049)
Python