a13668349935 / OctaveConv_pytorch

Pytorch implementation of Octave convolution

OctaveConv_pytorch

Pytorch implementation of Octave convolution with other similar operation

This is third parity implementation(un-official) of Following Paper which are talked inRecente_Convolution.pdf:

1. Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution. paper
2. Adaptively Connected Neural Networks.(CVPR 2019) paper
3. Res2net:A New Multi-scale Backbone Architecture paper

Plan

1. add Res2Net bolock with SE-layer (done)
2. add Adaptive-Convolution: both pixel-aware and dataset-aware (done)
3. add HetConv(optional): if I have time :)
4. Train on Cifar ()
5. Train on Imagenet (): Who can help me train this repo on Imagenet

Usage

check model files under the nn floder.

from nn.OCtaveResnet import resnet50
from nn.res2net import se_resnet50
from nn.AdaptiveConvResnet import PixelAwareResnet50, DataSetAwareResnet50

model = resnet50().cuda()
model = se_resnet50().cuda()
model = PixelAwareResnet50().cuda()
model = DataSetAwareResnet50().cuda()

Reference:

1. OctaveConv: MXNet implementationhere
2. AdaptiveCov: Offical tensorflow implementationhere

License

MIT License